LLMs & Agents at PyCon DE & PyData

Large language models, agents, RAG, and applied AI across every edition.

283 talks across all editions.

Workshop: What do we still need to learn? [no-video]

Paula Gonzalez Avalos, Sebastian Neubauer, Dr. Kristian Rother · 2026

AI agents are reshaping how we work, how we code, how we search — and quietly, how we think about ourselves as practitioners. The ground is shifting. And nobody has all the answers yet. That is exactly why we are...
When Space Weather Breaks Your GPS: Building an Explainable Early Warning System

Vincenzo Ventriglia · 2026

Have you ever happened to use GPS and realised that it is not working properly? The Sun could be responsible. In this talk, I present a **real-world machine learning forecasting system** designed to predict a Space...
When LLMs Are Too Big: Building Cost-Efficient High-Throughput ML Systems for E-Commerce Cataloging

Tobias Senst, Bastian Wandt · 2026

E-commerce cataloging at idealo operates at extreme scale: 4.5 billion offers from 50,000+ shops across six countries, with peak ingestion rates of 4.8 million offers per minute. While large language models (LLMs)...
What Breaks When Automatic Speech Recognition Systems Go Multilingual

Rashmi Nagpal · 2026

Building machine learning models for audio deepfake detection seems straightforward until datasets span multiple languages, such as Hindi, Korean, Mandarin, and German. In practice, multilingual Automatic Speech...
Vibe NLP for Applied NLP

Ines Montani · 2026

One of the hardest parts of applied NLP has always been breaking down complex business problems into machine learning components. It's so hard because it requires domain expertise and reasoning about the specific use...
Using Sensor Fusion and ML to Navigate Underground When GPS Fails

Étienne Tremblay · 2026

In the twisting vaults of a subway, metro, or U-Bahn, there’s often no reliable cell service, wifi, or GPS. Which means riders had no good way of keeping track of their stops or ETA when underground. After collecting...
Type Errors for Better Agent-Assisted Development

Kyle Into · 2026

Type annotations aren't just for humans anymore. As AI coding agents write more Python, type checkers offer something unique: fast, concrete diagnostics about what went wrong and where. In this talk, I explore...
Tracking Knowledge Diversity in LLM-Generated Responses.

Sarah Masud · 2026

As large language models (LLMs)-powered “AI highlights” become the first information people see on the Web, a key question arises: how much variety and perspective do these systems actually deliver for...
The foundation model revolution for tabular data

Frank Hutter · 2026

Tabular data, spreadsheets organized in rows and columns, are ubiquitous across healthcare, business and finance. The fundamental prediction task of filling in missing values of a label column based on the rest of...
The Day the Agent Started Lying (Politely)

Asya Melnik · 2026

You deploy an agent to automatically route incoming customer support tickets. At first, it is a clear win: response times improve, customers are happier, and support teams finally get some rest. Then time passes....
The Art of the Optimal: A Pythonic Approach to Complex Decision-Making

Justine Broihan · 2026

As Python developers, we frequently tackle complex decision-making problems by writing custom scripts and heuristic algorithms. While a standard greedy algorithm might provide a quick, intuitive fix, it rarely finds...
Stop Waiting, Start Shipping: Real-World Strategy for Open-Source LLMs

Sebastian Raschka, Alexander CS Hendorf · 2026

Chinese and American open-source LLMs are competing head-to-head — from DeepSeek and Qwen to Llama and Mistral. The model landscape is broader than ever, yet in Germany the debate still circles around waiting for the...
State of In-Browser ML: WebAssembly, WebGPU, and the Modern Stack

Oleh Kostromin, Iryna Kondrashchenko · 2026

What if you could run real data/ML workflows right in your browsers - sandboxed, with no installation or sending your data anywhere? Such an approach would have tons of benefits: it is easy to distribute, safer by...
Start-Ups & Investors

Ina Schlie, Carlina Bennison, Sara Jourdan, Jovana Walter · 2026

Starting a company doesn't require a garage or an MBA — it takes a real problem, a strong team, and someone willing to turn a project into a product. This panel brings together founders, investors, and startup...
SQL is Dead, Long Live SQL: Engineering reliable analytics agent from scratch

Mehdi Ouazza, Dumky de Wilde · 2026

Is it still worth learning SQL in 2026, or can we just "chat" with our data? This hands-on tutorial explores that exact question by pushing Text-to-SQL to its absolute limits. This won't be just happy paths; we will...
Solving Marketplace Cold Start at Scale with Ranking

Theodore Meynard · 2026

Cold start is a critical bottleneck for marketplaces: new items lack behavioral signals and reviews, so ranking models under-expose them, delaying the very signals needed to rank them well. This talk shares practical...
Small Language Models for Tool Calling Are Better Than You Think

Gabi Kadlecova · 2026

Large language models have been widely used in tool-calling workflows thanks to their strong performance in generating appropriate function calls. However, due to their size and cost, they are inaccessible to...
Simplifying RAG Document Pipelines with Multimodal Embeddings

Arne Grobrügge · 2026

In RAG-based systems, the main challenge is often not tuning the LLM itself, but making documents available in a form that can be retrieved reliably. In enterprise settings, the dominant input format is still PDF,...
Securing AI Agentic Systems: Enforcing Safety Constraints in AI Agent

John Robert · 2026

AI agents are increasingly deployed with autonomy: calling tools, accessing data, modifying systems, and making decisions without human supervision. While prompts and guardrails are often presented as safety...
Roll for Architecture: DungeonPy – A D&D Companion as Server + Thin Clients

Francesco Conte · 2026

### **DungeonPy** – an interactive Dungeon&Dragons app for remote campaigns As a matter of fact, tabletop RPGs are secretly distributed systems: one canonical world state, many clients, lossy links (players), and...
Restaurants around train stations are bad and I can prove it

Dennis Schulz · 2026

Have you ever asked yourself: Why is there no good food option close to this main station? This talk tries to find out if this is a systematic problem - using publicly available data and Google APIs. After this talk,...
Rediscovering single-node processing: When does it make sense to move from Spark to Polars?

Jonas Böer · 2026

As data engineers, we are used to spinning up a Spark Cluster every time we want to do data processing and handle the overhead that comes with using such a mighty framework. But is this really necessary? In this talk...
Python Hates Being PID 1: Writing Container-Aware Code for Kubernetes

Kavish Nareshchandra Dahekar · 2026

On Kubernetes, your Python app runs in a hostile environment, fighting for resources in a straitjacket, bombarded with signals, and being killed and ruthlessly dragged back to life time and again. This is in stark...
Production ML across 2015-2035: A Journey to the Past and the Future

Alejandro Saucedo · 2026

This talk is an exciting journey that revisits the past decade of Production Machine Learning from 2015 until now, and provides a pragmatic outlook of the next decade towards 2035. We’ll revisit some of the...
Post-Processing and Visualization of Astrophysical Data with PyPLUTO

Giancarlo Mattia · 2026

Modern scientific workflows increasingly rely on interactive analysis, reproducibility, and high-quality visualisation. **PyPLUTO** is a Python package designed to explore, analyse, and visualise numerical...
Personalized Restaurant Recommendations at Scale combining Transformer with Gradient-Boosted Ranking

Marcel Kurovski, Steffen Klempau · 2026

Wolt’s Universal Venue Ranker (UVR) is a large-scale, sequence-aware ranking model for personalized restaurant recommendations, deployed across more than 30 countries. UVR replaces three previously independent...
Panel: Evolution, Revolution, or Illusion? The Future of Python and Coding in the Age of AI

Sebastian Neubauer, Markus Klein, Asya Melnik, Serhii Sokolenko, Ines Montani · 2026

Software engineering is changing fast. With AI now writing and reasoning about code, does it still make sense to learn Python or any language at all? Is this the evolution of our craft, a true revolution, or just...
Pair & Share: How formal Mentoring pushed REWE Analytics to a new level

Axel Buddendiek · 2026

As one of Europe’s largest retail corporations, REWE Group owns and manages prominent supermarket chains such as REWE and PENNY, among many other subsidiaries. In this talk I will give a brief overview of how we...
Open Table Formats in the Wild™ - Reloaded: Vortexing Ducks over Floating Icebergs

Franz Wöllert · 2026

Open table formats have *almost* freed us from vendor lock-in. They form a critical building block of the modern, composable data stack. The most prominent open table format is Apache Iceberg - not only because of...
On Interventional Generalisation

Andy Kitchen · 2026

If I do X instead of Y, will I get the outcome I want? What about in a new unseen situation? Making predictions alone is pointless, one wants to act in the world. Furthermore one must act in situations that are...
Offline Fallback for a Mobile LoRaWAN Gateway

Jannis Lübbe · 2026

LoRaWAN gateways typically depend on cloud-based network servers, creating a vulnerability during internet outages. This talk presents a hybrid solution: a Raspberry Pi-based mobile gateway that operates on The...
Octopus AutoML: Extracting Signal from Small and High-Dimensional Data

Nils Haase, Andreas Wurl · 2026

Many machine learning tools assume abundant, independent data, rely on a single data split plus cross-validation, and leave test-set separation to the user. In application-driven domains such as industrial materials...
No, you can't 'eval' your way to fairness

Laura Summers · 2026

Fairness is fundamentally not tractable to classic optimisation techniques. It's not a state of the world, it's an experience of it. No technology is fair in a vacuum - fairness can only be understood when a...
Mastering the Hex: A Case Study in Reinforcement Learning for Strategy Games

Simon Hedrich · 2026

What does it take to build an AI that learns to play strategy games from scratch? Over the past year, I chose to explore this question out of personal fascination with game AI — as a seminar project for college, but...
Making bad CLIs fun with Small Language Models

Moritz Bauer · 2026

Command Line Interfaces (CLIs) offer an efficient and powerful way to interact with software, but poorly designed interfaces can be incredibly frustrating. Complicated parameter names and unconventional formats can...
Leveraging Hexagonal Architecture When Building Applications

Luke Gerstner · 2026

Hexagonal architecture in software development is a design pattern that has existed for more than 20 years and remains highly applicable today as we enter an era where LLMs are increasingly used as development tools....
Learnings Building DevOps as a Software Engineer

Gaweng Tan · 2026

When I joined my current company as a software engineer, I encountered a blank slate: no CI/CD pipelines, no deployment infrastructure, barely any monitoring—in short, no software infrastructure at all. This talk...
It Works on My Machine: Why LLM Apps Fail Users (Not Tests)

Thomas Prexl, Frank Rust · 2026

LLM applications frequently pass tests but fail users in production. This talk examines the gap between evaluation metrics and user experience through three lenses: **Expectations** (what "working" means to users),...
In Praise of Documentation: Tools, Tips & Techniques for Literate Programming in the AI Age

Stephen · 2026

This talk has one simple message: *please document your code*. If you attend my talk, you'll hear me explain why I praise documentation, and why you should too. While writing documentation is generally acknowledged...
Hype, Hope, or Headache? Making Sense of GenAI, LLMs, and AI Agents with Anecdotal Evidence

Sebastian Neubauer · 2026

After nearly 20 years in data science, from MLPs, SVMs, and random forests to deep learning, I’ve seen many “revolutions” come and go. The current tectonic shift around GenAI and LLMs feels different from previous...
How We Built an Inclusive Data Organization: Careers, Community & 50% Women

Xia He-Bleinagel · 2026

Building inclusive data teams and sustainable career paths is a challenge many organizations struggle with—especially in fast-growing, highly technical environments. Data careers are often portrayed as linear, while...
How to compare apples with oranges: Proper evaluation of article-level demand forecasts

Stefan Birr, Mones Raslan · 2026

How do you evaluate performance when you predict more than 10 million time series each day? While a good plot can be worth more than a thousand metrics for a single time series, with large-scale machine learning...
"Honey, I vibe coded some crypto" - Security in the age of LLMS

Gabriela Bogk · 2026

What only a few years ago started out as smart tab completion turned into a way of working in which a growing number of programmers don't even bother to open up an IDE anymore. Let's take a moment to contemplate the...
Hierarchical Models in MMM: Can Structure beat data size?

Mohamed Amine Jebari · 2026

In every marketing project, teams strive to find more data, a longer timeframe, and more detailed splits, just to fix noisy channel attribution. But what if structure played a bigger role than size and volume? In...
Heat: scaling the Python scientific stack to HPC systems

Claudia Comito, Thomas Saupe · 2026

Python’s scientific stack (NumPy/SciPy) is often confined to single-node execution. When datasets exceed local memory, researchers face a steep learning curve, typically choosing between complex manual distribution...
From Ticket to Draft: How Munich Automates Citizen Inquiries with AI

Leon Lukas · 2026

The City of Munich is modernizing its communication: With the transition to the Zammad ticketing system, there is a unique opportunity to not only manage citizen inquiries but to proactively process them using...
From Scratch to Scale: Turning LLM Code into Architecture Insights

Sebastian Raschka · 2026

Python has been at the center of my work in machine learning and AI for more than a decade. It is where I start from scratch, experiment with ideas, and build systems that help me understand how large language models...
From Research Models to SLAs: Operationalizing TSFMs with Python

Jeyashree Krishnan, Catarina Filipe · 2026

Time series foundation models (TSFMs) such as Chronos, Lag-Llama, TimesFM, and Siemens’ own GTT have shown strong generalization capabilities across diverse forecasting tasks. However, integrating these models into a...
From Prompt to Production: How to use AI Code Assistants for Python Data Systems

Serhii Sokolenko · 2026

**Code-generating LLMs have matured** to the point where they can reliably scaffold **data pipelines and data agents**, when used in a **supervised, engineering-first workflow**. This tutorial demonstrates how to...
From Pixel to Payouts: A Multi-Agent System for Real-Time Insurance Claims Processing

Claudio Giorgio Giancaterino · 2026

The traditional process for auto damage evaluation is relatively slow, subjective, and prone to fraud. With this presentation, the goal is to show a Multi-Agent System designed for the automation and standardization...
Foundation Models in Forecasting: Are We There Yet? Lessons from the Trenches

Dr. Irena Bojarovska · 2026

The rise of time-series foundation models like Chronos-2 and TimesFM has sparked a debate: can a single pre-trained model replace the specialized "local" models we have tuned for years? We moved beyond the hype to...
Escape the Hype: Teaching LLM Concepts Through an Interactive AI Factory Game

Vadim Vlasov, Eric Glaser, Lisa Amrhein · 2026

Everyone talks about LLMs, RAG, and AI agents - but who truly understands them? Marketing promises magic while documentation assumes expertise. Recent research from Gartner reveals the consequences: only 8% of HR...
Empowering Data Scientists with Zero Platform Friction: Deploying Streamlit & Friends in 3 Minutes

Bernhard Schäfer, Nicolas Renkamp · 2026

A data scientist builds a Streamlit or Dash prototype, the business wants to validate it, and the hard parts begin: getting access to live data, making the app available company-wide, and ensuring every user only...
Embedding Data Science in IoT devices with MicroPython and emlearn

Jon Nordby · 2026

Python is the standard solution for many machine learning and data science applications, from large cloud systems, to workstations, and even on larger embedded or robotics systems. But as we move down into more...
Dynamic Knowledge Graphs

Jakob Leander Müller · 2026

Traditional RAG systems struggle to understand holistic connections in distributed, constantly changing knowledge sources that characterize real-world organizations. While document-based approaches using vector...
Don’t call your LLM too often! How to build your dialog graph with confidence and sleep at night.

Evgeniya Ovchinnikova, Andrei Beliankou · 2026

Keywords: **Explainable AI, enhanced RAG, GraphRAG, LLMOps, dialog system evaluation.** Designing reliable dialog flows for LLM-based systems remains challenging once conversations require branching, correction, or...
Do you know how well your model is doing? Evaluate your LLMs

Cheuk Ting Ho · 2026

Large Language Models (LLMs) are becoming central to modern applications, yet effectively evaluating their performance remains a significant challenge. How do you objectively compare different models, benchmark the...
Destructive Testing: 10 Practical Ways to Expose Hidden Application Risks

Pascal Puchtler · 2026

Modern applications rarely fail in obvious ways. Instead, they break at the edges: unexpected inputs, race conditions, misused APIs, and assumptions nobody realized they were making. This talk presents ten practical...
Demystifying Agentic AI Using Small Language Models

Serhii Sokolenko · 2026

The AI world is buzzing with claims about “agentic intelligence” and autonomous reasoning. Behind the hype, however, a quieter shift is taking place: Small Language Models (SLMs) are proving capable of many reasoning...
Causal Inference through the lens of probabilistic programming

Dr. Juan Orduz · 2026

Causal inference asks the hardest question in data science: "What would have happened if things were different?" While traditional methods often rely on rigid rules, statistical tests or "black box" adjustments,...
Catch the LLM if you Can: Watermarking LLMs

Subhosri Basu · 2026

With Large Language Models (LLMs), generating high-quality text and images is easy and so is misusing it. As AI-generated content becomes harder to distinguish from human generated content, developers are...
Building Secure Environments for CLI Code Agents

Harald Nezbeda · 2026

AI code agents like Claude Code are powerful but require careful isolation. Learn how to run them in secure containers with persistent credentials, API logging, and complete filesystem isolation—protecting your host...
Building Non-Biased Synthetic Datasets: What Actually Works (and What Fails)

Shiva Banasaz Nouri · 2026

Synthetic data is often presented as an easy fix for missing or sensitive datasets, but in practice, it can silently introduce bias, leakage, and misleading evaluation results. This talk presents a practical,...
Building MCP at the Speed of Hype: Principles That Outlast the Trends

Rahkakavee Baskaran, Friederike Bauer · 2026

Every week, development in AI brings us another groundbreaking release, another model version, another must-have integration. In this rapidly shifting landscape, how does one build production systems that won’t be...
Building Agentic Systems with Python, LangGraph, MCP, and A2A

Holger Nösekabel · 2026

Building an agentic system that collects and evaluates company information in real time—without curated datasets—requires solving difficult challenges in data acquisition, quality control, and agent orchestration....
Beyond Vibe-Coding: A Practitioner's Guide to Spec-Driven Development in AI Engineering

Alina Dallmann · 2026

AI-assisted coding became the default. Tools like GitHub Copilot, Cursor, and Claude can generate hundreds of lines of Python in seconds. However, the real challenge isn't how fast we generate code — it's how we...
Beyond Stateless: Why Your Web Service Architecture is Fighting Against Performance

Heiner Wolf · 2026

We've been told for years that stateless services are the holy grail of scalable web architectures. But what if this foundational principle is actually hurting development speed and runtime performance? Coding agents...
Beyond Kafka and S3: Python Data Pipelines with HTTP-Native Bytestreams

Johannes Dröge · 2026

Real-time bytestreams between systems in different organizations or secured environments, whether for batch dataset delivery or continuous streaming, are surprisingly hard. Traditional solutions fall short: message...
Before You Ship Your Agent: An Agent Builder’s Primer on Jailbreaking Attacks

Simonas Černiauskas · 2026

Before you ship an AI agent to production, you need to understand how it can be broken. Jailbreaking and prompt injection attacks are not edge cases—they are an inevitable consequence of deploying real-world,...
AI Is Changing the Game: Building Modular, AI-Ready Platforms on Top of Legacy Systems

Werner Gothein · 2026

AI is fundamentally changing how quickly business and domain teams can create new logic, validations, and insights. In regulated environments, this new speed collides head-on with legacy systems, monolithic...
AI Evals Done Right: From Vibes to Confident Decisions

Martin Seeler · 2026

Testing traditional software is "simple"... same input, same output. LLMs? Not so much. Same prompt, different result every time. So how do you actually know if your AI product is good? Most teams struggle with this....
Agent-Based Hyperparameter Optimization for Gradient Boosted Trees

Huijo Kim · 2026

### Teaching an LLM to Tune GBDT — and Beyond Hyperparameter optimization for gradient boosted tree models is a repetitive yet cognitively demanding task. Practitioners must combine statistical intuition with...
Accuracy Is Overrated: Ship Stable Forecasts (Without Lying to Yourself)

Illia Babounikau · 2026

Forecasting talks love a clean ending: “and then we improved WMAPE by 3.7%.” Nice. Now put that model into production without suffering from instability. You retrain your model on a few new weeks of data and suddenly...
Accelerate FastAPI Development with OpenAPI Generator

Dr. Evelyne Groen, Kateryna Budzyak · 2026

Develop FastAPI applications faster with the contract-first approach using the OpenAPI Generator, no GenAI required. **To attend this workshop, please install the openapi generator.** For details, please visit the...
7 Anti-Lessons from Building a PydanticAI Agent: Mistakes We Made So You Don't Have To

Joshua Görner · 2026

Life sciences compliance isn't forgiving. When your software helps companies navigate FDA regulations, ISO 13485, and EU MDR, "move fast and break things" isn't an option. Audit trails matter. Documentation is...
5 Years of NiceGUI: What We Learned About Designing Pythonic UIs

Falko Schindler · 2026

NiceGUI has grown from a small experiment into a widely used framework for building modern web-based user interfaces entirely in Python. After five years of development, thousands of users, and countless design...
Zero Code Change Acceleration: familiar interfaces and high performance ▶ Recording 📝 Transcript

Tim Head · 2025

The PyData ecosystem is home to some of the best and most popular tools for doing data-science. Every data-scientist alive today has used pandas and scikit-learn and even Large Language Models know how to use them!...
What's inside the box? Building a deep learning framework from scratch. ▶ Recording 📝 Transcript

Oleh Kostromin · 2025

Explore the inner workings of deep learning frameworks like TensorFlow and PyTorch by building your own in this workshop. We will start with the fundamental automatic differentiation mechanics and proceed to...
What do a tree and the human brain have in common-a not so serious introduction to digital pathology ▶ Recording 📝 Transcript

Daniel Hieber · 2025

While trees and human brains don't share that many properties regarding their domain, the analysis of the height of a tree and cancer in human brains does. This talk provides a not-so-serious introduction to the...
Vector Streaming: The Memory Efficient Indexing for Vector Databases ▶ Recording 📝 Transcript

Sonam Pankaj, Akshay Ballal · 2025

Vector databases are everywhere, powering LLMs. But indexing embeddings, especially multivector embeddings like ColPali and Colbert, at a bulk is memory intensive. Vector streaming solves this problem by...
Unlocking the Predictive Power of Relational Data with Automated Feature Engineering ▶ Recording 📝 Transcript

Alexander Uhlig · 2025

Relational data can be a goldmine for classical Machine Learning applications — yet extracting useful features from multiple tables, time windows, and primary-foreign key relationships is notoriously difficult. In...
Unforgettable, that's what you are: Evaluating Machine Unlearning and Forgetting ▶ Recording 📝 Transcript

Katharine Jarmul · 2025

Can deep learning/AI models forget? In this talk, you'll explore the realm of machine unlearning, where researchers and practitioners aim to remove memorized examples from machine learning models. This is relevant...
Transformers for Game Log Data ▶ Recording 📝 Transcript

Fabian Hadiji · 2025

The Transformer architecture, originally designed for machine translation, has revolutionized deep learning with applications in natural language processing, computer vision, and time series forecasting. Recently,...
Towards Intelligent Monitoring: Detecting Degraded Flame Torch Nozzles ▶ Recording 📝 Transcript

Dominik Falkner · 2025

Flame cutting is a method where metals are efficiently cut using precise control of the oxygen jet and consistent mixing of fuel gas. The condition of the nozzle is changing over time: deposits formed during the...
The future of AI training is federated ▶ Recording 📝 Transcript

Chong Shen Ng · 2025

Since it’s introduction in 2016, Federated Learning (FL) has become a key paradigm to AI models in scenarios when training data cannot leave its source. This applies in many industrial settings where centralizing...
The Future of AI: Building the Most Impactful Technology Together ▶ Recording 📝 Transcript

Leandro von Werra · 2025

In this talk, Leandro will examine the significant benefits of combining open source principles with artificial intelligence. He will walk through the need for openness in language models to build trust, maintain...
The Foundation Model Revolution for Tabular Data ▶ Recording 📝 Transcript

Noah Hollmann, Frank Hutter · 2025

What if we could make the same revolutionary leap for tables that ChatGPT made for text? While foundation models have transformed how we work with text and images, tabular / structured data (spreadsheets and...
The Forecast Whisperer: Secrets of Model Tuning Revealed ▶ Recording 📝 Transcript

Illia Babounikau · 2025

Forecasting can often feel like interpreting vague signals—unclear yet full of potential. In this talk, we’ll cover advanced techniques for tuning forecasting models in professional settings, moving beyond the basics...
Taking Control of LLM Outputs: An Introductory Journey into Logits ▶ Recording 📝 Transcript

Emek Gözlüklü · 2025

This talk explores logits - the raw confidence scores that language models generate before selecting each token. Understanding and manipulating these scores gives you practical control over how models generate text....
supplyseer: Computational Supply Chain with Python ▶ Recording 📝 Transcript

Jako Rostami · 2025

This talk introduces supplyseer, an open-source Python library that brings advanced analytics to Supply Chain and Logistics. By combining time series embedding techniques, stochastic process modeling, and...
Streamlining Python deployment with Pixi: A Perspective from production ▶ Recording 📝 Transcript

Dennis Weyland · 2025

In our quest to improve Python deployments, we explored Pixi, a tool designed to enhance dependency management within the Conda ecosystem. This talk recounts our experience integrating Pixi into a setup used in...
Securing RAG Pipelines with Fine Grained Authorization ▶ Recording 📝 Transcript

Sohan Maheshwar · 2025

Using LLMs and AI in your Enterprise? Make sure you build Fine Grained Authorization to ensure your LLMs access only the data they are authorized to. This talk will show how you can build Relationship Based Access...
Securing Generative AI: Essential Threat Modeling Techniques

Elizaveta Zinovyeva · 2025

Generative AI development introduces unique security challenges that traditional methods often overlook. This talk explores practical threat modeling techniques tailored for AI practitioners, focusing on real-world...
Secure “Human in the Loop” Interactions for AI Agents ▶ Recording 📝 Transcript

Juan Cruz Martinez · 2025

Explore the power of Human-in-the-Loop (HITL) for GenAI agents! Learn how to build AI systems that augment your abilities, not replace your judgment, especially when high-stakes actions are involved. This session...
Scraping LEGO for Fun: A Hacky Dive into Dynamic Data Extraction ▶ Recording 📝 Transcript

Peter Lodri · 2025

Unlock the full potential of modern web scraping by combining Python, Scrapy, and Playwright to extract data from dynamic, JavaScript-heavy sites—exemplified by LEGO product pages. This talk introduces Model Context...
Scaling Python: An End-to-End ML Pipeline for ISS Anomaly Detection with Kubeflow ▶ Recording 📝 Transcript

Christian Geier, Henrik Sebastian Steude · 2025

Building and deploying scalable, reproducible machine learning pipelines can be challenging, especially when working with orchestration tools like Slurm or Kubernetes. In this talk, we demonstrate how to create an...
Scalable Python and SQL Data Engineering without Migraines ▶ Recording 📝 Transcript

Dirk Jung · 2025

This session is for data and ML engineers with a basic understanding of data engineering and Python. It shows how to easily use Python code in Snowflake Notebooks to create data pipelines. By the end, you’ll know how...
🦀 Rüstzeit: Asynchronous Concurrency in Python & Rust

Jamie Coombes · 2025

Many Python developers are enhancing their Rust knowledge and want to take the next step in translating their understanding of advanced concepts like asynchronous programming. In this talk, I'll help you take that...
Responsible AI with fmeval - an open source library to evaluate LLMs ▶ Recording 📝 Transcript

Mia Chang · 2025

The term "Responsible AI" has seen a threefold increase in search interest compared to 2020 across the globe. As developers, the questions like "How can we build large language model-enabled applications that are...
Reinforcement Learning Without a PhD: A Python Developer’s Journey ▶ Recording 📝 Transcript

Jochen Luithardt · 2025

Reinforcement Learning (RL) has shown superhuman performance in games and is already delivering value in Big Tech. But despite its potential, RL remains largely inaccessible to most developers. Why? Because...
Reinforcement Learning for Finance ▶ Recording 📝 Transcript

Dr. Yves J. Hilpisch · 2025

Reinforcement Learning and related algorithms, such as Deep Q-Learning (DQL), have led to major breakthroughs in different fields. DQL, for example, is at the core of the AIs developed by DeepMind that achieved...
PyLadies Panel: AI Skills & Careers ▶ Recording 📝 Transcript

Tereza Iofciu, Jesper Dramsch, Anastasia Karavdina, Guadalupe Canas Herrera · 2025

As generative AI and autonomous agents rapidly transform the workplace, the skills required to thrive are evolving just as quickly. This panel will explore the essential AI skills that are driving career growth.
Practical Python/Rust: Building and Maintaining Dual-Language Libraries ▶ Recording 📝 Transcript

Ben Brandt · 2025

Building performant Python often means reaching for C extensions. This talk explores an alternative: leveraging Rust to create blazing-fast Python modules that also benefit the Rust ecosystem. I will share practical...
PosePIE: Replace Your Keyboard and Mouse With AI-Driven Gesture Control ▶ Recording 📝 Transcript

Daniel Stolpmann · 2025

In this talk, we show how to leverage publicly available tools to control any game or program using hand or body movements. To achieve this, we introduce PosePIE, an open-source programmable input emulator that...
PDFs - When a thousand words are worth more than a picture (or table). ▶ Recording 📝 Transcript

Caio Benatti Moretti · 2025

PDF, a must-have in RAG systems, ensures visual fidelity across platforms and devices, at the expense of compromising what would be the core condition for computers to properly process and interpret text: semantics....
Optimizing in the Python Ecosystem – Powered by Gurobi ▶ Recording 📝 Transcript

Silke Horn · 2025

Join us as we explore integrating Gurobi and prescriptive analytics into your Python ecosystem. In this session, you’ll discover model-building techniques that leverage NumPy and SciPy.sparse as well as the data...
Optimizing Energy Tariffing System with Formal Concept Analysis and Dash ▶ Recording 📝 Transcript

Dr. Irina Smirnova-Pinchukova · 2025

As a data scientist, I value the power of insightful visualizations to unlock unique interpretations of complex data. In my talk, I will introduce an elegant mathematical framework called Formal Concept Analysis...
Open Table Formats in the Wild: From Parquet to Delta Lake and Back ▶ Recording 📝 Transcript

Franz Wöllert · 2025

Open table formats have revolutionized analytical, columnar storage on cloud object stores with critical features like ACID compliance and enhanced metadata management, once exclusive to proprietary cloud data...
Oh, no! Users love my GenAI-Prototype and want to use it more. ▶ Recording 📝 Transcript

Thomas Prexl, Frank Rust · 2025

Demos and prototypes for generative AI (GenAI) projects can be quickly created with tools like Streamlit, offering impressive results for users within hours. However, scaling these solutions from prototypes to robust...
Offline Disaster Relief Coordination with OpenStreetMap and FastAPI ▶ Recording 📝 Transcript

Jannis Lübbe · 2025

In natural disaster scenarios, reliable communication is crucial. This talk presents a solution for disaster relief coordination using OpenStreetMap vector maps hosted on a local device in the emergency vehicle with...
Multi-tenant Conversational Analytics ▶ Recording 📝 Transcript

Rodel van Rooijen · 2025

Ever wondered how to use GenAI to enable self-service analytics through prompting? In this talk, I will share my experience of building a multi-tenant conversational analytics set-up that is built into a...
Modern NLP for Proactive Harmful Content Moderation ▶ Recording 📝 Transcript

Daryna Dementieva · 2025

Despite an array of regulations implemented by governments and social media platforms worldwide (i.e. famous DSA), the problem of digital abusive speech persists. At the same time, rapid advances in NLP and large...
Mastering Demand Forecasting: Lessons from Europe's Largest Retailer ▶ Recording 📝 Transcript

Moreno Schlageter, Yovli Duvshani · 2025

Ever craved your favorite dish, only to find its key ingredient missing from the store? You're not alone - stock outs can have significant consequences for businesses, resulting in frustrated customers and lost...
Machine Reasoning and System 2 Thinking ▶ Recording 📝 Transcript

Andy Kitchen · 2025

Raw large language models struggle with complex reasoning. New techniques have emerged that allow these models to spend more time thinking before giving an answer. Direct token sampling can be seen as system-1...
LLM Inference Arithmetics: the Theory behind Model Serving ▶ Recording 📝 Transcript

Luca Baggi · 2025

Have you ever asked yourself how parameters for an LLM are counted, or wondered why Gemma 2B is actually closer to a 3B model? You have no clue about what a KV-Cache is? (And, before you ask: no, it's not a Redis...
Lessons learned in bringing a RAG chatbot with access to 50k+ diverse documents to production ▶ Recording 📝 Transcript

Bernhard Schäfer, Nico Mohr · 2025

Retrieval-Augmented Generation (RAG) chatbots are a key use case of GenAI in organizations, allowing users to conveniently access and query internal company data. A first RAG prototype can often be created in a...
Langfuse, OpenLIT, and Phoenix: Observability for the GenAI Era ▶ Recording 📝 Transcript

Emanuele Fabbiani · 2025

Large Language Models (LLMs) are transforming digital products, but their non-deterministic behaviour challenges predictability and testing, making observability essential for quality and scalability. This talk...
Jeannie: An Agentic Field Worker Assistant ▶ Recording 📝 Transcript

Andrei Beliankou, Jose Moreno Ortega · 2025

Jeannie is an LLM-based agentic workflow implemented in Python to automate task management for field workers in the energy sector. This system addresses inefficiencies and safety risks in tasks like PV panel...
Is your LLM any good at writing? Benchmarking on creative writing and editing tasks ▶ Recording 📝 Transcript

Azamat Omuraliev · 2025

Many LLM benchmarks focus on reasoning and coding tasks. These are exciting tasks! But the majority of LLM usage is still in writing and editing related tasks, and there's a surprising lack of benchmarks on these. In...
Is Prompt Engineering Dead? How Auto-Optimization is Changing the Game ▶ Recording 📝 Transcript

Iryna Kondrashchenko, Oleh Kostromin · 2025

The rise of LLMs has elevated prompt engineering as a critical skill in the AI industry, but manual prompt tuning is often inefficient and model-specific. This talk explores various automatic prompt optimization...
Intuitive A/B Test Evaluations for Coders ▶ Recording 📝 Transcript

Thomas Mayer · 2025

A/B testing is a critical tool for making data-driven decisions, yet its statistical underpinnings—p-values, confidence intervals, and hypothesis testing—are often challenging for those without a background in...
Interactive end-to-end root-cause analysis with explainable AI in a Python Shiny App

Simone Lederer, Julius Möller · 2025

We demonstrate a pure Python solution for exploring and understanding datasets using state-of-the-art machine learning and explainable AI techniques. Our application features a reactive dashboard built with Shiny,...
Information Retrieval Without Feeling Lucky: The Art and Science of Search

Anja Pilz · 2025

Search is everywhere, yet effective Information Retrieval remains one of the most underestimated challenges in modern technology. While Retrieval-Augmented Generation has captured significant attention, the...
How to use Data Science Superpowers in real life, a Bayesian perspective

Tim Lenzen · 2025

In the data science field, we use all these powerful methods to solve important problems. Most of the time, we do this very well because our data science and machine-learning toolbox fits the problems we tackle quite...
Hands-On LLM Security: Attacks and Countermeasures You Need to Know! ▶ Recording 📝 Transcript

Clemens Hübner, Florian Teutsch · 2025

Dive into the vulnerabilities of LLMs and learn how to prevent them From prompt injection to data poisoning, we’ll demonstrate real-world attack scenarios and reveal essential countermeasures to safeguard your applications.
Guardians of the Code: Safeguarding Machine Learning Models in a Climate Tech World ▶ Recording 📝 Transcript

Doreen Sacker · 2025

LLMs, Machine learning and AI are everywhere, yet their security is often overlooked, leaving your systems vulnerable to serious attacks. What happens when someone tampers with your model’s input, poisons your...
Going Global: Taking code from research to operational open ecosystem for AI weather forecasting ▶ Recording 📝 Transcript

Jesper Dramsch · 2025

When I was hired as a Scientist for Machine Learning, experts said ML would never work in weather forecasting. Nowadays, I get to contribute to Anemoi, a full-featured ML weather forecasting framework used by...
Generative-AI: Usecase-Specific Evaluation of LLM-powered Applications ▶ Recording 📝 Transcript

Dr. Homa Ansari · 2025

This talk addresses the critical need for usecase-specific evaluation of Large Language Model (LLM)-powered applications, highlighting the limitations of generic evaluation benchmarks in capturing domain-specific...
Generative AI Monitoring with PydanticAI and Logfire

Marcelo Trylesinski · 2025

In this talk, we will explore how the integration of PydanticAI and Logfire creates a powerful foundation for generative AI applications. We'll demonstrate how these tools combine to form sophisticated AI workflows...
From Trees to Transformers: Our Journey Towards Deep Learning for Ranking ▶ Recording 📝 Transcript

Theodore Meynard, Mihail Douhaniaris · 2025

GetYourGuide, a global marketplace for travel experiences, reached diminishing returns with its XGBoost-based ranking system. We switched to a Deep Learning pipeline in just nine months, maintaining high throughput...
From Tensors to Clouds — A Practical Guide to Zarr V3 and Zarr-Python 3 ▶ Recording 📝 Transcript

Sanket Verma · 2025

A key feature of the Python data ecosystem is the reliance on simple but efficient primitives that follow well-defined interfaces to make tools work seamlessly together (Cf. http://data-apis.org/). NumPy provides an...
From stockouts to happy customers: Proven solutions for time series forecasting in retail ▶ Recording 📝 Transcript

Robert Haase · 2025

Time series forecasting in the retail industry is uniquely challenging: Datasets often include stockouts that censor actual demand, promotional events cause irregular demand spikes, new product launches face...
From Queries to Confidence: Ensuring SQL Reliability with Python ▶ Recording 📝 Transcript

Anna Varzina · 2025

SQL remains a foundational component of data-driven applications, but ensuring the accuracy and reliability of SQL logic is often challenging. SQL testing can be cumbersome, time-consuming, and error-prone. However,...
From Idea to Integration: An Intro to the Model Context Protocol (MCP) ▶ Recording 📝 Transcript

Julian Beck · 2025

The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models with diverse data sources and enabling interactions with other systems. In this talk, we’ll introduce the MCP standard...
From Algorithm to Action: Building a DIY Distributed Trading Platform with Open Source ▶ Recording 📝 Transcript

Eugen Geist · 2025

In this talk, we'll explore how you can implement your own distributed system for algorithmic trading leveraging the power of open source without being dependent on trading bot providers. We will discuss different...
Forecast of Hourly Train Counts on Rail Routes Affected by Construction Work ▶ Recording 📝 Transcript

Sebastian Folz, Dr Maren Westermann · 2025

Construction work in national railroad networks often disrupts train traffic, making it vital to estimate hourly train numbers for effective re-routing. Traditionally managed by humans, this process has been...
expectation: A modern take on statistical A/B testing with e-values and martingales

Jako Rostami · 2025

This talk introduces a novel Python library for statistical testing using e-values, offering a refreshing alternative to traditional p-values. We'll explore how this approach enables real-time sequential testing,...
Enhancing RAG with Fast GraphRAG and InstructLab: A Scalable, Interpretable, and Efficient Framework ▶ Recording 📝 Transcript

Tuhin Sharma · 2025

Retrieval Augmented Generation (RAG) has become a cornerstone in enriching GenAI outputs with external data, yet traditional frameworks struggle with challenges like data noise, domain specialization, and...
Electify - Retrieval-Augmented Generation for Voter Information in the 2024 European Election ▶ Recording 📝 Transcript

Christian Liedl · 2025

In general elections, voters often face the challenge of navigating complex political landscapes and extensive party manifestos. To address this, we developed Electify, an interactive application that utilizes...
Distributed file-systems made easy with Python's fsspec ▶ Recording 📝 Transcript

Einat Orr, Barak Amar · 2025

The cloud native revolution has impacted all aspects of engineering, and data engineering is not exempt. One of the ongoing challenges in the data engineering world remains the local and distributed cloud native...
Decoding Topics: A Comparative Analysis of Python’s Leading Topic Modeling Libraries Using Climate C ▶ Recording 📝 Transcript

Dr. Lisa Andreevna Chalaguine · 2025

Topic modelling has come a long way, evolving from traditional statistical methods to leveraging advanced embeddings and neural networks. Python’s diverse library ecosystem includes tools like Latent Dirichlet...
Conquering PDFs: document understanding beyond plain text ▶ Recording 📝 Transcript

Ines Montani · 2025

NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work...
Conformal Prediction: uncertainty quantification to humanise models ▶ Recording 📝 Transcript

Vincenzo Ventriglia · 2025

Quantifying model uncertainties is critical to improve model reliability and make sound decisions. Conformal Prediction is a framework for uncertainty quantification that provides mathematical guarantees of true...
Composable AI: Building Next-Gen AI Agents with MCP ▶ Recording 📝 Transcript

Martin Seeler · 2025

At Blue Yonder, we're embarking on a journey toward building composable AI agents using Model Context Protocol (MCP). We're discovering firsthand the challenges of integrating diverse products and APIs into useful,...
Code & Community: The Synergy of Community Building and Task Automation ▶ Recording 📝 Transcript

Cosima Meyer · 2025

The Python community is built on a culture of support, inclusion, and collaboration. Sustaining this welcoming environment requires intentional community-building efforts, which often involve repetitive or...
Career Path Experience Stories ▶ Recording 📝 Transcript

Kristina Khvatova · 2025

As part of the PyConDE & PyData 2025 Conference, we would like to present an initiative aimed primarily at students and those just starting their careers in computer science. Our goal is to showcase the diverse...
Building versatile operating setups for real world use and testing with Python and the Raspberry Pi ▶ Recording 📝 Transcript

Jens Nie · 2025

**Rosenxt** is the host of a number of ventures aiming to provide next level solutions for demanding problems in a variety of industries based on decades of engineering excellence. Some of them address challenges in...
Building Serverless Python AI skills as WASM components ▶ Recording 📝 Transcript

Moritz Althaus · 2025

Frameworks like llama-stack and langchain allow for quick prototyping of generative AI applications. However, companies often struggle to deploy these applications into production quickly. This talk explores the...
Building Reliable AI Agents for Publishing: A DSPy-Based Quality Assurance Framework ▶ Recording 📝 Transcript

Simonas Černiauskas · 2025

As publishers increasingly adopt AI agents for content generation and analysis, ensuring output quality and reliability becomes critical. This talk introduces a novel quality assurance framework built with DSPy that...
Building an Open Source RAG System for the United Nations Negotiations on Global Plastic Pollution ▶ Recording 📝 Transcript

Rahkakavee Baskaran, Teresa Kroesen, Anna-Lisa Wirth · 2025

Plastic pollution is a significant global challenge. Every year, millions of tons of plastic enter the oceans, impacting marine ecosystems and human health. To address this issue, the United Nations is negotiating a...
Building a Self-Hosted MLOps Platform with Kubernetes ▶ Recording 📝 Transcript

Josef Nagelschmidt · 2025

Many managed MLOps platforms, while convenient, often fall short in providing flexibility, requiring complex integrations, and causing vendor lock-in. In this talk, we’ll share our experience transitioning from...
Building a HybridRAG Document Question-Answering System ▶ Recording 📝 Transcript

Darya Petrashka · 2025

Retrieval Augmented Generation (RAG) is a powerful technique for searching across unstructured documents, but it often falls short when the task demands an understanding of intricate relationships between entities....
Build a personalized Commute agent in Python with Hopsworks, LangGraph and LLM Function Calling ▶ Recording 📝 Transcript

Javier de la Rúa Martínez · 2025

The invention of the clock and the organization of time in zones have helped synchronize human activities across the globe. While timekeepers are better at planning and sticking to the plan, time optimists somehow...
Bridging the gap: unlocking SAP data for data lakes with Python and PySpark via SAP Datasphere

Rostislaw Krassow · 2025

SAP's data often remains locked away, hindering the creation of a complete data picture. This talk presents a hands-on proof of concept leveraging SAP Datasphere, Python and PySpark to bridge an Azure-based, data...
Blazing-Fast Python in Your Database: Unlocking Data Science at Scale with Exasol ▶ Recording 📝 Transcript

Alexander Stigsen · 2025

What if your Python models could run inside your database—at scale, with parallel execution, and zero data movement? Meet Exasol: a high-performance Analytics Engine with native Python support and a massively...
Bias Meets Bayes: A Bayesian Perspective on Improving Model Fairness ▶ Recording 📝 Transcript

Vince Nelidov · 2025

Bias in machine learning models remains a pressing issue, often disproportionately affecting the most vulnerable groups in society. This talk introduces a Bayesian perspective to effectively tackle these challenges,...
Beyond FOMO — Keeping Up-to-Date in AI ▶ Recording 📝 Transcript

Carsten Frommhold · 2025

The rapid evolution of AI technologies, particularly since the emergence of Large Language Models, has transformed the data science landscape from a field of steady progress to one of constant breakthroughs. This...
Beyond DALL-E: Advanced Image Generation Workflows with ComfyUI ▶ Recording 📝 Transcript

René Fa · 2025

Image generation using AI has made huge progress over the last years, and many people still think that DALL-E with a text prompt is the best way to generate images. There are well-known models like Stable Diffusion...
Beyond Basic Prompting: Supercharging Open Source LLMs with LMQL's Structured Generation ▶ Recording 📝 Transcript

Christiaan Swart · 2025

This intermediate-level talk demonstrates how to leverage Language Model Query Language (LMQL) for structured generation and tool usage with open-source models like Llama. You will learn how to build a RAG system...
Beyond Alembic and Django Migrations ▶ Recording 📝 Transcript

Rotem Tamir · 2025

ORMs like Django and SQLAlchemy have become indispensable in Python development, simplifying the interaction between applications and databases. Yet, their built-in schema migration tools often fall short in projects...
Beyond Agents: What AI Strategy Really Needs in 2025 ▶ Recording 📝 Transcript

Alexander CS Hendorf · 2025

Artificial intelligence is no longer confined to models and APIs—it now shapes systems, hardware, and real-world agents. In this talk, I reflect on strategic insights gained at NVIDIA’s GTC 2025, where AI’s...
Benchmarking Time Series Foundation Models with sktime ▶ Recording 📝 Transcript

Benedikt Heidrich · 2025

Recent time series foundation models such as LagLlama, Chronos, Moirai, and TinyTimesMixer promise zero-shot forecasting for arbitrary time series. One central claim of foundation models is their ability to perform...
Autonomous Browsing using Large Action Models ▶ Recording 📝 Transcript

Nico Kreiling, Arne Grobrügge · 2025

The browser serves as our gateway to the internet—the largest repository of knowledge in human history. Proficiency in its use is a core skill across nearly all professions and is becoming increasingly important for...
Are LLMs the answer to all our problems? ▶ Recording 📝 Transcript

Dr. Maria Börner · 2025

Generative AI models have shaken up the German market. Since the release of ChatGPT, AI is available and usable for everyone. The number of ChatGPT-based agents is growing rapidly, but concerns about privacy,...
AI coding agent - what it is, how it works and is it good for developers

Cheuk Ting Ho · 2025

In this talk, we will have a deeper technical look at AI coding agents, their design, and how they can carry out coding tasks with the support of large language models. We will look at the journey from the user...
AI Agents of Change: Creating, Reflecting, and Monetizing ▶ Recording 📝 Transcript

Tereza Iofciu, Paloma Oliveira · 2025

Create, reflect, and earn—with purpose. In this workshop, you’ll not only build your own AI agent but also confront the ethical questions it raises, from its impact on jobs to its potential for social good. Together,...
Agentic AI: Build a Multi-Agent Application with CrewAI ▶ Recording 📝 Transcript

Alessandro Romano · 2025

This hands-on tutorial will dive into the fundamentals of building multi-agent systems using the CrewAI Python library. Starting from the basics, we’ll cover key concepts, explore advanced features, and guide you...
Accuracy Is Not Enough: Building Trustworthy AI with Conformal Prediction ▶ Recording 📝 Transcript

Chris Aivazidis · 2025

Building a good scoring model is just the beginning. In the age of critical AI applications, understanding and quantifying uncertainty is as crucial as achieving high accuracy. This talk highlights conformal...
3 Ways to Speed up Your Regression Modeling in Python ▶ Recording 📝 Transcript

Alexander Fischer · 2025

Linear Regression is the workhorse of statistics and data science. Some data scientists even go as far and argue that "linear regression is all you need". In this talk, we will introduce three ways to run regression...
Your Model _Probably_ Memorized the Training Data ▶ Recording 📝 Transcript

Katharine Jarmul · 2024

I know you probably don't want to hear about it, but your deep learning model probably memorized some of its training data. In this talk, we'll review active research on deep learning and memorization, particularly...
Would you rely on ChatGPT to dial 911? A talk on balancing determinism and probabilism in production machine learning systems ▶ Recording 📝 Transcript

Nicolas Guenon des Mesnards · 2024

In the last year there hasn’t been a day that passed without us hearing about a new generative AI innovation that will enhance some aspect of our lives. On a number of tasks large probabilistic systems are now...
Whispered Secrets: Building An Open-Source Tool To Live Transcribe & Summarize Conversations ▶ Recording 📝 Transcript

John Sandall · 2024

Are you secretly a spy and/or passionate about open-source? Maybe you don't trust a cloud-hosted service with your highly classified information, or perhaps you like to build things for yourself. In this...
Using ML to find out the "Why"? A Tutorial in Causal Machine Learning

Oliver Schacht, Jan Teichert-Kluge · 2024

Machine learning is mostly used for predicting outcome variables. But in many cases, we are interested in causal questions: Why do customers churn? What is the effect of a price change on sales? How can we optimize...
Using LLMs to Create Knowledge Graphs From a Large Corpus of Parliamentary Debates ▶ Recording 📝 Transcript

Usman · 2024

Large Language Models (LLMs) have proven to be incredibly powerful on a range of tasks. They do however, have certain limitations when the input context becomes significantly large. Solutions such as Retrieval...
Unlock the Power of Dev Containers: Build a Consistent Python Development Environment in Seconds! ▶ Recording 📝 Transcript

Thomas Fraunholz · 2024

In this talk, we will explore the basic concepts of Dev Containers and demonstrate how they can support your everyday development as a Python programmer, data scientist, or machine learning engineer. With Dev...
🌳 The taller the tree, the harder the fall. Determining tree height from space using Deep Learning and very high resolution satellite imagery 🛰️ ▶ Recording 📝 Transcript

Ferdinand Schenck · 2024

A case study of how we use Deep Learning based photogrammetry to calculate the height of trees from very high resolution satellite imagery. We show the substantial improvement achieved by switching from classical...
The pragmatic Pythonic data engineer ▶ Recording 📝 Transcript

Robson Junior · 2024

Learn to make practical decisions in data engineering with Python's vast ecosystem. Avoid blindly following market guidelines and consider the reality of your situation for better performance and architecture.
The evolution of Feature Stores ▶ Recording 📝 Transcript

Olamilekan Wahab · 2024

Feature Stores have become an important component of the machine learning lifecycle. They have been particularly pivotal in bridging the gap between data engineering and machine learning workflows(experimentation,...
The AI Revolution Will Not Be Monopolized: How open-source beats economies of scale, even for LLMs ▶ Recording 📝 Transcript

Ines Montani · 2024

With the latest advancements in Natural Language Processing and Large Language Models (LLMs), and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with...
That’s it?! Dealing with unexpected data problems ▶ Recording 📝 Transcript

Simon Pressler · 2024

Drawing on experience with multiple consulting projects, this talk shares experiences on how to deal with unexpected data problems. We are discussing how fare purely technical solutions as well as domain knowledge...
Tailored and Trending: Key learnings from 3 years of news recommendations

Dr. Christian Leschinski · 2024

Every day, we engage with news, and more often, these are curated by recommendation engines. Building such an algorithm poses some unique challenges, different from movie or product recommendations: articles have a...
Tackling the Cold Start Challenge in Demand Forecasting ▶ Recording 📝 Transcript

Alexander Meier, Daria Mokrytska · 2024

In this talk, we address the Cold Start problem in Demand Forecasting, focusing on scenarios where historical data is scarce or nonexistent. This constitutes a common situation in practice, such as with the launch of...
Select ML from Databases ▶ Recording 📝 Transcript

Gregor Bauer · 2024

This talk introduces a new workflow for building your machine learning models using the capabilities of modern databases that support machine learning use cases natively. There is an overview of how machine learning...
Safeguarding Privacy and Mitigating Vulnerabilities: Navigating Security Challenges in Generative AI ▶ Recording 📝 Transcript

John Robert · 2024

Generative AI (GenAI) has significantly improved our daily lives, prompting a focus on its integration into products and our routines. However, the growing importance of GenAI brings along significant concerns...
Reinforcement Learning: Bridging The Gap Between Research and Applications ▶ Recording 📝 Transcript

Michael Panchenko · 2024

Reinforcement learning (RL) has great potential for industrial applications, but few mature software frameworks exist to facilitate its use. This talk discusses efforts to improve the software landscape for RL,...
RAG for a medical company: the technical and product challenges ▶ Recording 📝 Transcript

Noé Achache · 2024

[RAG (Retrieval Augmented Generation)](https://www.pinecone.io/learn/retrieval-augmented-generation/) is the process of querying a (large) set of documents with natural language, leveraging vector search and llms....
(PyLadies Panel) Reflecting Within: Challenging Narratives in Tech Feminism ▶ Recording 📝 Transcript

Cheuk Ting Ho, Katharine Jarmul, Paloma Oliveira, Naa Ashiorkor Nortey · 2024

For the third year in a role, the PyLadies Panel at PyCon PyData engages with a broader audience on critical issues related to gender disparities, ethics, and the ongoing importance of women-focused tech groups....
Put your RAG to the test: Component-per-component evaluation of our LLM-powered airplane manufacturing assistant

Nataliia Kees · 2024

Your RAG-powered LLM application might look pretty convincing at first glance, but how do you really know if it’s any good? And how do you justify the design choices you make? In this talk, you will learn about the...
Polars and Time Series: what it can do, and how to overcome any limitation ▶ Recording 📝 Transcript

Marco Gorelli · 2024

Time series analysis is ubiquitous in applied data science because of the value it delivers. In order to do effective time series analysis, you need to know your tools well. Polars has excellent built-in time series...
Personalizing Carousel Ranking on Wolt's Discovery Page: A Hierarchical Multi-Armed Bandit Approach ▶ Recording 📝 Transcript

Marcel Kurovski, Steffen Klempau · 2024

Wolt's Discovery page serves as the primary gateway for millions of weekly users exploring diverse cuisines and products. With over 130,000 merchants in 25 countries, presenting relevant content poses a unique...
No More Raw SQL: SQLAlchemy, ORMs & asyncio ▶ Recording 📝 Transcript

Aya Elsayed, Rhythm Patel · 2024

Managing a database and synchronizing service data representation with the database can be tricky. In this workshop, you’ll learn how to use SQLAlchemy, a powerful SQL toolkit, to simplify this task. We’ll cover how...
Moving from Offline to Online Machine Learning with River ▶ Recording 📝 Transcript

Tun Shwe · 2024

The foundations of machine learning were built on offline batch processing techniques for model training and inference. As organisations become more dependent on real-time data, the technological trend for machine...
Mojo 🔥 - Is it Python's faster cousin or just hype? ▶ Recording 📝 Transcript

Jamie Coombes · 2024

On 2023-05-02, the tech sphere buzzed with the release of Mojo 🔥, a new programming language developed by Chris Lattner, renowned for his work on Clang, LLVM, and Swift. Billed as "Python's faster cousin," and "The...
Missing Data, Bayesian Imputation and People Analytics with PyMC ▶ Recording 📝 Transcript

Nathaniel Forde · 2024

We demonstrate a range of different approaches to missing data imputation in employee engagement survey data. Contrasting frequentist style full-information maximum likelihood approaches with more direct Bayesian...
Marketing Media Mix Models with Python & PyMC: a Case Study ▶ Recording 📝 Transcript

Emanuele Fabbiani · 2024

In today's digital landscape, traditional analytics struggle with understanding marketing ROI, especially with evolving privacy norms. But Python and its ecosystem come to the rescue. In this talk, we will discuss...
Machine Learning on microcontrollers using MicroPython and emlearn ▶ Recording 📝 Transcript

Jon Nordby · 2024

This presentation will show you how to deploy machine learning models to affordable microcontroller-based systems - using the Python that you already know. Combined with sensors, such as microphone, accelerometer or...
Leveraging the Art of Parallel Unit Testing in Django ▶ Recording 📝 Transcript

Azan Bin Zahid, Syed Ansab Waqar Gillani · 2024

Unit testing is a fundamental practice in software development, ensuring the reliability and maintainability of code. However, in the context of monolith repositories, executing unit tests efficiently becomes a...
Lessons learned from deploying Machine Learning in an old-fashioned heavy industry ▶ Recording 📝 Transcript

Robert Meyer · 2024

About 5 years ago my co-founder and I launched alcemy, a Machine Learning startup to help decarbonize the cement and concrete supply chain. I experienced first hand moving from a simple proof of concept, a ML model...
Jupyter Notebooks for Print Media ▶ Recording 📝 Transcript

Tim Paine · 2024

In this talk, we will discuss leveraging Jupyter Notebooks to generate print media - books, magazine and newspaper articles, business reports, academic papers, etc. We will motivate the problem, introduce a library...
Improve LLM-based Applications with Fallback Mechanisms ▶ Recording 📝 Transcript

Bilge Yücel · 2024

While RAG addresses the common LLM pitfalls, challenges like handling out-of-domain queries still persist. Learn the significance of fallback mechanisms to tackle these issues gracefully, incorporating strategies...
I achieved peak performance in python, here's how ... ▶ Recording 📝 Transcript

Dishant Sethi · 2024

In the ever-evolving landscape of software development, crafting code that not only functions flawlessly but also operates at peak performance is a skill that sets exceptional developers apart. This talk delves into...
How to Do Monolingual, Multilingual, and Cross-lingual Text Classification in April, 2024 ▶ Recording 📝 Transcript

Daryna Dementieva · 2024

In 2023, the field of NLP was again flurried -- the appearing of powerful closed- and opens-source LLMs opened new possibility for texts processing. However, many questions about these models usability for typical...
Haystack 2.0: the story of a rewrite ▶ Recording 📝 Transcript

Silvano Cerza · 2024

To rewrite or not to rewrite: it's a major question. Releasing new software versions with breaking changes can be disruptive to a community, but sometimes they are necessary in the long run to move forward. Haystack...
From LLM as oracle to LLM as translator - our journey from theory to everyday’s practice in a corporate setting with dmGPT (and python)

Emma Haley, Niklas Lederer · 2024

Last year, dm-drogeriemarkt was among the first big German companies launching a tool for the coworkers to be able to unlock the power of LLMs in a secure setting. At the beginning, dmGPT was only a user interface...
From idea to production in a day: Leveraging Azure ML and Streamlit to build and user test machine learning ideas quickly ▶ Recording 📝 Transcript

Florian Roscheck · 2024

Getting a machine learning solution in front of users usually takes some time. The data science tech stack is full of time traps and infrastructure issues might slow down deployment. The Azure Machine Learning...
FlixBus CitySnap: How we use GenAI and not only to collect captivating images for cities and confirm their locations ▶ Recording 📝 Transcript

Andrei Chernov · 2024

Have you ever wondered how travel e-commerce companies gather photos of cities? While I can't speak for everyone, I will demonstrate the innovative approach we are using at Flix. In recent years, text-to-text models...
Exploring Zarr: From Fundamentals to Version 3.0 and Beyond ▶ Recording 📝 Transcript

Sanket Verma · 2024

A key feature of the Python data ecosystem is the reliance on simple but efficient primitives that follow well-defined interfaces to make tools work seamlessly together (Cf. http://data-apis.org/). NumPy provides an...
Everything you need to know about change-point detection 📝 Transcript

Charles Truong · 2024

Change-point detection is a crucial processing step when dealing with long and non-stationary time series. It has been applied in many contexts, such as human activity recognition, speech/sound processing and...
DDataflow: An open-source end-to-end testing framework for ML pipelines ▶ Recording

Theodore Meynard, Jean Machado · 2024

In the realm of machine learning, the complexity of data pipelines often hinders rapid experimentation and iteration. This talk will introduce [DDataflow](https://github.com/getyourguide/DDataFlow), an innovative...
Content Recommendation with Graphs: From Basic Walks to Neural Networks ▶ Recording 📝 Transcript

Dr. Mirza Klimenta · 2024

Discover how graph algorithms are transforming content recommendation in this insightful talk. We'll journey from the basics of graph-based models, exploring simple graph walks, to the cutting-edge realm of Graph...
Cloud? No Thanks! I’m Gonna Run GenAI on My AI PC ▶ Recording 📝 Transcript

Adrian Boguszewski, Dmitriy Pastushenkov · 2024

In this speech, we want to introduce an AI PC, a single machine that consists of a CPU, GPU, and NPU (Neural Processing Unit) and can run GenAI in seconds, not hours. Besides the hardware, we will also show the...
Can ChatGPT convince you to get a COVID19 vaccine? Comparing ChatGPT to an expert system - which one is more convincing? ▶ Recording 📝 Transcript

Dr. Lisa Andreevna Chalaguine · 2024

This study explores the efficacy of chatbots as dialogical argumentation systems for behaviour change, focusing on vaccine hesitancy during the COVID-19 pandemic. A Python-based chatbot, developed in 2021, engaged in...
Building Professional Voice AI with Vocode ▶ Recording 📝 Transcript

Lev Konstantinovskiy · 2024

Dive into the world of AI voice agents with Vocode, the leading framework for creating interactive, voice-based AI assistants. In this talk, we'll explore how Vocode integrates speech-to-text, response generation,...
Build TikTok's Personalized Real-Time Recommendation System in Python with Hopsworks ▶ Recording 📝 Transcript

Aleksey Veresov · 2024

The real-time recommendations engine in Tiktok, Monolith, is so good it has been described as "digital crack" (by Andrej Karpathy, former head of AI at Tesla). In this tutorial, we will build the core components of...
Build an AI Document Inquiry Chat with Offline LLMs ▶ Recording 📝 Transcript

Pavithra Eswaramoorthy, Philip Meier · 2024

As we descend from the peak of the hype cycle around Large Language Models (LLMs), chat-based document inquiry systems have emerged as a high-value practical use case. Retrieval-Augmented Generation (RAG) is a...
Build a personalized Bitcoin (BTC) virtual assistant in Python with Hopsworks and LLM function calling ▶ Recording 📝 Transcript

Javier de la Rúa Martínez · 2024

The human ambitious desire to get rich without effort has been a major driving force behind the popularity of cryptocurrencies like Bitcoin and Ethereum. However, their high volatility makes them too unpredictable,...
Breaking AI Boundaries: Fairness Metrics in Unstructured Data Domains ▶ Recording 📝 Transcript

Daniel Klitzke · 2024

This presentation addresses the rare use of machine learning fairness metrics in domains with indirect human impact, e.g., automotive engineering. We briefly map out the space of use cases to examine the necessity,...
Beyond Deployment: Exploring Machine Learning Inference Architectures and Patterns ▶ Recording 📝 Transcript

Tim Elfrink · 2024

This talk is about setting up robust and scalable machine learning systems for high-throughput real-time predictions and large numbers of users. It is meant for ML engineers and people who work with data and want to...
A Retrieval Augmented Generation system to query the scikit-learn documentation ▶ Recording 📝 Transcript

Guillaume Lemaitre · 2024

The scikit-learn website currently employs an "exact" search engine based on the Sphinx Python package, but it has limitations: it cannot handle spelling mistakes and queries based on natural language. To address...
A conceptual and practical introduction to Hilbert Space Gaussian Process (HSGP) approximation methods ▶ Recording 📝 Transcript

Dr. Juan Orduz · 2024

In this talk, we explore a new method to approximate Gaussian processes using spectral analysis methods, known as the Hilbert Space Gaussian process (HSGP) approximation. This technique allows us to use and fit...
Writing Plugin Friendly Python Applications ▶ Recording 📝 Transcript

Travis Hathaway · 2023

In modern software engineering, plugin systems are a ubiquitous way to extend and modify the behavior of applications and libraries. When software is written in a way that is plugin friendly, it encourages the use of...
Why GPU Clusters Don't Need to Go Brrr? Leverage Compound Sparsity to Achieve the Fastest Inference Performance on CPUs

Damian Bogunowicz · 2023

Forget specialized hardware. Get GPU-class performance on your commodity CPUs with compound sparsity and sparsity-aware inference execution. This talk will demonstrate the power of compound sparsity for model...
“Who is an NLP expert?” - Lessons Learned from building an in-house QA-system

Nico Kreiling, Alina Bickel · 2023

Innovations such as sentence-transformers, neural search and vector databases fueled a very fast development of question-answering systems recently. At scieneers, we wanted to test those components to satisfy our own...
When A/B testing isn’t an option: an introduction to quasi-experimental methods ▶ Recording 📝 Transcript

Inga Janczuk · 2023

Identification of causal relationships through running experiments is not always possible. In this talk, an alternative approach towards it, quasi-experimental frameworks, is discussed. Additionally, I will present...
Use Spark from anywhere: A Spark client in Python powered by Spark Connect ▶ Recording 📝 Transcript

Martin Grund · 2023

Over the past decade, developers, researchers, and the community have successfully built tens of thousands of data applications using Spark. Since then, use cases and requirements of data applications have evolved:...
The State of Production Machine Learning in 2023 ▶ Recording 📝 Transcript

Alejandro Saucedo · 2023

As the number of production machine learning use-cases increase, we find ourselves facing new and bigger challenges where more is at stake. Because of this, it's critical to identify the key areas to focus our...
The Spark of Big Data: An Introduction to Apache Spark ▶ Recording 📝 Transcript

Pasha Finkelshteyn · 2023

Get ready to level up your big data processing skills! Join us for an introductory talk on Apache Spark, the distributed computing system used by tech giants like Netflix and Amazon. We'll cover PySpark DataFrames...
The Battle of Giants: Causality vs NLP => From Theory to Practice ▶ Recording 📝 Transcript

Aleksander Molak · 2023

With an average of 3.2 new papers published on Arxiv every day in 2022, causal inference has exploded in popularity, attracting large amount of talent and interest from top researchers and institutions including...
Teaching Neural Networks a Sense of Geometry ▶ Recording 📝 Transcript

Jens Agerberg · 2023

By taking neural networks back to the school bench and teaching them some elements of geometry and topology we can build algorithms that can reason about the shape of data. Surprisingly these methods can be useful...
Prompt Engineering 101: Beginner intro to LangChain, the shovel of our ChatGPT gold rush."

Lev Konstantinovskiy · 2023

A modern AI start-up is a front-end developer plus a prompt engineer" is a popular joke on Twitter. This talk is about LangChain, a Python open-source tool for prompt engineering. You can use it with completely...
Pragmatic ways of using Rust in your data project ▶ Recording 📝 Transcript

Christopher Prohm · 2023

Writing efficient data pipelines in Python can be tricky. The standard recommendation is to use vectorized functions implemented in Numpy, Pandas, or the like. However, what to do, when the processing task does not...
Performing Root Cause Analysis with DoWhy, a Causal Machine-Learning Library ▶ Recording 📝 Transcript

Patrick Blöbaum · 2023

In this talk, we will introduce the audience to [DoWhy](https://www.pywhy.org/dowhy), a library for causal machine-learning (ML). We will introduce typical problems where causal ML can be applied and will...
Observability for Distributed Computing with Dask ▶ Recording 📝 Transcript

Hendrik Makait · 2023

Debugging is hard. Distributed debugging is hell. Dask is a popular library for parallel and distributed computing in Python. Dask is commonly used in data science, actual science, data engineering, and machine...
Most of you don't need Spark. Large-scale data management on a budget with Python ▶ Recording 📝 Transcript

Guillem Borrell · 2023

The Python data ecosystem has matured during the last decade and there are less and less reasons to rely only large batch process executed in a Spark cluster, but with every large ecosystem, putting together the key...
Maximizing Efficiency and Scalability in Open-Source MLOps: A Step-by-Step Approach ▶ Recording 📝 Transcript

Paul Elvers · 2023

This talk presents a novel approach to MLOps that combines the benefits of open-source technologies with the power and cost-effectiveness of cloud computing platforms. By using tools such as Terraform, MLflow, and...
Incorporating GPT-3 into practical NLP workflows ▶ Recording 📝 Transcript

Ines Montani · 2023

In this talk, I'll show how large language models such as GPT-3 complement rather than replace existing machine learning workflows. Initial annotations are gathered from the OpenAI API via zero- or few-shot learning,...
Improving Machine Learning from Human Feedback ▶ Recording 📝 Transcript

Erin Mikail Staples, Nikolai · 2023

Large generative models rely upon massive data sets that are collected automatically. For example, GPT-3 was trained with data from “Common Crawl” and “Web Text”, among other sources. As the saying goes — bigger...
Hyperparameter optimization for the impatient ▶ Recording 📝 Transcript

Martin Wistuba · 2023

In the last years, Hyperparameter Optimization (HPO) became a fundamental step in the training of Machine Learning (ML) models and in the creation of automatic ML pipelines. Unfortunately, while HPO improves the...
How to build observability into a ML Platform ▶ Recording 📝 Transcript

Alicia Bargar · 2023

As machine learning becomes more prevalent across nearly every business and industry, making sure that these technologies are working and delivering quality is critical. In her talk, Alicia will discuss the...
Honey, I broke the PyTorch model >.< - Debugging custom PyTorch models in a structured manner

Clara Hoffmann · 2023

When building PyTorch models for custom applications from scratch there's usually one problem: The model does not learn anything. In a complex project, it can be tricky to identify the cause: Is it the data? A bug in...
Grokking Anchors: Uncovering What a Machine-Learning Model Relies On

KIlian Kluge · 2023

Assessing the robustness of models is an essential step in developing machine-learning systems. To determine if a model is sound, it often helps to know which and how many input features its output hinges on. This...
Fear the mutants. Love the mutants. ▶ Recording 📝 Transcript

Max Kahan · 2023

Developers often use code coverage as a target, which makes it a bad measure of test quality. Mutation testing changes the game: create mutant versions of your code that break your tests, and you'll quickly start to...
evosax: JAX-Based Evolution Strategies ▶ Recording 📝 Transcript

Robert Lange · 2023

Tired of having to handle asynchronous processes for neuroevolution? Do you want to leverage massive vectorization and high-throughput accelerators for evolution strategies (ES)?...
Delivering AI at Scale ▶ Recording 📝 Transcript

Severin Schmitt, Anna Achenbach, Thorsten Kranz · 2023

Everybody knows our yellow vans, trucks and planes around the world. But do you know how data drives our business and how we leverage algorithms and technology in our core operations? We will share some “behind the...
Building a Personal Assistant With GPT and Haystack: How to Feed Facts to Large Language Models and Reduce Hallucination.

Mathis Lucka · 2023

Large Language Models (LLM), like ChatGPT, have shown miraculous performances on various tasks. But there are still unsolved issues with these models: they can be confidently wrong and their knowledge becomes...
BHAD: Explainable unsupervised anomaly detection using Bayesian histograms ▶ Recording 📝 Transcript

Alexander Vosseler · 2023

The detection of outliers or anomalous data patterns is one of the most prominent machine learning use cases in industrial applications. I present a Bayesian histogram anomaly detector (BHAD), where the number of...
Bayesian Marketing Science: Solving Marketing's 3 Biggest Problems ▶ Recording 📝 Transcript

Dr. Thomas Wiecki · 2023

In this talk I will present two new open-source packages that make up a powerful and state-of-the-art marketing analytics toolbox. Specifically, PyMC-Marketing is a new library built on top of the popular Bayesian...
AutoGluon: AutoML for Tabular, Multimodal and Time Series Data ▶ Recording 📝 Transcript

Caner Turkmen, Oleksandr Shchur · 2023

AutoML, or automated machine learning, offers the promise of transforming raw data into accurate predictions with minimal human intervention, expertise, and manual experimentation. In this talk, we will introduce...
Advanced Visual Search Engine with Self-Supervised Learning (SSL) Representations and Milvus

Antoine Toubhans, Noé Achache · 2023

Image retrieval is the process of searching for images in a large database that are similar to one or more query images. A classical approach is to transform the database images and the query images into embeddings...
Actionable Machine Learning in the Browser with PyScript ▶ Recording 📝 Transcript

Valerio Maggio · 2023

PyScript brings the full PyData stack in the browser, opening up to unprecedented use cases for interactive data-intensive applications. In this scenario, the web browser becomes a ubiquitous computing platform,...
Accelerating Public Consultations with Large Language Models: A Case Study from the UK Planning Inspectorate

Michele Dallachiesa, Andreas Leed · 2023

Local Planning Authorities (LPAs) in the UK rely on written representations from the community to inform their Local Plans which outline development needs for their area. With an average of 2000 representations per...
You shall not share! ▶ Recording 📝 Transcript

Gönül Aycı · 2022

Online social network users frequently share personal information online. While each post is targeted to a certain audience, it is not always easy to judge what the privacy implications of shared content will be. To...
Unsupervised shallow learning for fraud detection on marketplaces ▶ Recording 📝 Transcript

Andreu Mora · 2022

Combating fraud, scams and wrongdoings in large marketplaces and platforms that connect millions of individuals as sellers and shoppers poses a very exciting and also difficult problem. Adyen leverages massive...
The secret sauce of data science management ▶ Recording 📝 Transcript

Shir Meir Lador · 2022

The question - “how to become a successful data scientist?” is often discussed in conferences like these. Today I would like to address a second level question. How to make the success scale? How to build a DS team...
Squirrel - Efficient Data Loading for Large-Scale Deep Learning ▶ Recording 📝 Transcript

Dr. Thomas Wollmann · 2022

Data stall in deep learning training refers to the case where combined throughput of data loading and transformation is less than the consumption rate of the model, leading to idling of expensive GPU resources and...
Seeing the needle AND the haystack: single-datapoint selection for billion-point datasets

Jean-Luc Stevens · 2022

Python tools like Bokeh and Dash let you build custom Web-based interactive visualization apps and dashboards. While these solutions work well to visualize megabyte-sized datasets, web technologies (including WebGL)...
Secure ML: Automated Security Best Practices in Machine Learning ▶ Recording 📝 Transcript

Alejandro Saucedo · 2022

As data science capabilities scale, the core concept of security becomes growingly critical. In this talk we will introduce the security challenges and solutions for data science practitioners relevant to each of the...
`python-m5p` - M5 Prime regression trees in python, compliant with scikit-learn ▶ Recording 📝 Transcript

Sylvain Marié · 2022

Regression trees are powerful Machine Learning models capable of both flexibility in modeling as well as interpretability when the tree is not too deep. The M5 algorithm, introduced by Quinlan in 1992 to provide more...
Predictive Maintenance and Anomaly Detection for Wind Energy ▶ Recording 📝 Transcript

Tobias Hoinka · 2022

This talk will describe predictive modeling applications in wind turbine maintenance, the challenges of anomaly detection and ways to move to more automatic diagnoses by modeling past documented defects.
My forecast is better than yours! What does that even mean? ▶ Recording 📝 Transcript

Illia Babounikau · 2022

Forecasting is one of the most popular applications of Machine Learning. In the last decades, it went from large numbers, few factors, and simple algorithms to small numbers, many factors, and complex ML models....
Making MLOps uncool again ▶ Recording 📝 Transcript

David · 2022

Machine learning operations (MLOps) have gained attention among practitioners aiming to automate the development of Machine Learning models, attempting to mimic the impact of DevOps in software. However, MLOps...
Machine Learning Testing Ecosystem of Python ▶ Recording 📝 Transcript

Yunus Bulut · 2022

In this talk, I'll present the growing ecosystem of machine learning testing tools in Python. Machine learning validation and testing is an emerging concern in the MLOps domain and will become more so in the near...
Introduction to Uplift Modeling ▶ Recording 📝 Transcript

Dr. Juan Orduz · 2022

In this talk we introduce uplift modelling, a method to estimate causal effects of a treatment, e.g. a marketing campaign, to effectively target customers that are most likely to respond to it. We describe the most...
Inpsect and try to interpret your scikit-learn machine-learning models ▶ Recording 📝 Transcript

Guillaume Lemaitre · 2022

This tutorial presents the different inspection techniques currently available to inspect a machine-learning model developed with scikit-learn. In addition, we compare all these methods and pinpoint their limitations.
Honey, I shrunk the target variable! Common pitfalls when transforming the target variable and how to exploit transformations.

Florian Wilhelm · 2022

Feature engineering takes up a huge part in the work-life of a data scientist. Sometimes this doesn't stop at features but also the target variable itself is transformed leading to all kinds of unexpected...
Financial Portfolio Management with Deep Reinforcement Learning

T-Berger · 2022

This talk will answer the question, if a deep reinforcement agent can be trained to optimize a financial portfolio. And therefore outperform an etf-based benchmark while minimizing the risk and maximizing the return...
Detecting drift: how to evaluate and explore data drift in machine learning systems ▶ Recording 📝 Transcript

Emeli Dral · 2022

When your ML model is in production, you might observe input data and prediction drift. In absence of ground truth, drift can serve as a proxy for the model performance. But how exactly to evaluate it? In this talk,...
Data Science at Scale with Dask ▶ Recording 📝 Transcript

Richard Pelgrim · 2022

A Pythonic introduction to methods for scaling your data science and machine learning work to larger datasets and larger models with Dask, all while staying within the comfort of the tools and APIs you know and love...
Data Apis: Standardization of N-dimensional arrays and dataframes ▶ Recording 📝 Transcript

Stephannie Jimenez Gacha · 2022

We would like to introduce the consortium of Data APIs, where we will be presenting our motivation, objectives and progress of the standardization process after one year of activity. We will dive into a small history...
Come as you are: Transitioning from Science to Data Science ▶ Recording 📝 Transcript

Dr. Hannah Bohle · 2022

I would like to give a little insight into my journey from academia to industry. I started working as a data scientist after more than a decade in quantitative science and leaving my post-doc position in...
Biases in Language Models ▶ Recording 📝 Transcript

Sonam Pankaj · 2022

The talk is an attempt to measure biases in most popular language models and we propose a solution to reduce the bias, and promote social inclusion and diversity based on gender. We have covered both methods on...
Why you should (not) train your own BERT model for different languages or domains

Marianne Stecklina · 2019

Language models like BERT can capture general language knowledge and transfer it to new data and tasks. However, applying a pre-trained BERT to non-English text has limitations. Is training from scratch a good (and...
Where Linguistics meets Natural Language Processing ▶ Recording 📝 Transcript

Mariana Capinel · 2019

This talk explains how linguistics describes language - via phonetics-phonology, morphology, syntax, semantics and pragmatics. We will combine linguistic concepts with models through examples for NLP newbies.
Tackle the problems that really matter - leverage the power of data science in the service of humanity

Eva Schreyer, Lisa Zäuner · 2019

Data Science for Social Good Berlin (DSSG) brings together data scientist volunteers and nonprofit organisations that need support in tackling various data challenges. In this talk we will tell you how data science...
Play Stupid Games, Win Stupid Prizes ▶ Recording 📝 Transcript

James Powell · 2019

This is reserved for a James Powell in-promptu talk, stay tuned! This is reserved for a James Powell in-promptu talk, stay tuned!
Leveraging the advantages of Bayesian Methods to build a data science product using PyMC3 ▶ Recording 📝 Transcript

Korbinian Kuusisto · 2019

Bayesian models offer greater theoretical advantages compared to non-probabilistic methods, and also allow for more flexible model design. But how can one leverage these theoretical advantages to build a successful...
Kartothek – Table management for cloud object stores powered by Apache Arrow and Dask

Florian Jetter · 2019

Efficient data storage is an integral part of successful data applications. Cloud object stores prove to be an efficient choice but come with downsides when storing structured, tabular data. There is a way out, though.
Tickling not too thick ticks!

Giovanni Lanzani · 2018

Is it possible to take advantage of the cryptocurrencies hype to do market-neutral trading , that is: making money without risks? What about the low liquidity of the market? What challenges lie there? In this talk...
Solving Data Science Problems using a Jupyter Notebook and SAP HANA's in-database Machine Learning Libraries

Dr Frank Gottfried · 2018

During this talk we will present how a Data Scientist can work on datasets stored in SAP HANA's Database leveraging in-database machine learning libraries. Data will reside in the database and calcuations with be...
Case Study in Travel Business - Understanding agent connections using NetworkX

Cheuk Ting Ho · 2018

When you make a search for a hotel room, do you know how many travel agents are searching for you at the same time? In this talk, we demonstrate how to use the millions of searches a sourcing company received to...
Building your own conversational AI with open source tools ▶ Recording 📝 Transcript

Justina Petraitytė · 2018

Point-and-click tools like Dialogflow and LUIS are great for building simple prototypes of conversational agents. But they don’t scale well beyond answering simple questions. In this live-coding talk, you will learn...
Graphql in the Python World ▶ Recording

Nafiul Islam · 2017

So you've heard about this new thing called Graphql. What is it all about? What problems does it solve, and most importantly, how can you leverage it the python ecosystem? This talk is a tell all on what what Graphql...
Getting Scikit-Learn To Run On Top Of Pandas ▶ Recording

Ami Tavory · 2017

Scikit-Learn is built directly over numpy, Python's numerical array library. Pandas adds to numpy metadata and higher-level munging capabilities. This talk describes how to intelligently auto-wrap Scikit-Learn for...

LLMs & Agents at PyCon DE & PyData

Workshop: What do we still need to learn? [no-video]

When Space Weather Breaks Your GPS: Building an Explainable Early Warning System

When LLMs Are Too Big: Building Cost-Efficient High-Throughput ML Systems for E-Commerce Cataloging

What Breaks When Automatic Speech Recognition Systems Go Multilingual

Vibe NLP for Applied NLP

Using Sensor Fusion and ML to Navigate Underground When GPS Fails

Type Errors for Better Agent-Assisted Development

Tracking Knowledge Diversity in LLM-Generated Responses.

The foundation model revolution for tabular data

The Day the Agent Started Lying (Politely)

The Art of the Optimal: A Pythonic Approach to Complex Decision-Making

Stop Waiting, Start Shipping: Real-World Strategy for Open-Source LLMs

State of In-Browser ML: WebAssembly, WebGPU, and the Modern Stack

Start-Ups & Investors

SQL is Dead, Long Live SQL: Engineering reliable analytics agent from scratch

Solving Marketplace Cold Start at Scale with Ranking

Small Language Models for Tool Calling Are Better Than You Think

Simplifying RAG Document Pipelines with Multimodal Embeddings

Securing AI Agentic Systems: Enforcing Safety Constraints in AI Agent

Roll for Architecture: DungeonPy – A D&D Companion as Server + Thin Clients

Restaurants around train stations are bad and I can prove it

Rediscovering single-node processing: When does it make sense to move from Spark to Polars?

Python Hates Being PID 1: Writing Container-Aware Code for Kubernetes

Production ML across 2015-2035: A Journey to the Past and the Future

Post-Processing and Visualization of Astrophysical Data with PyPLUTO

Personalized Restaurant Recommendations at Scale combining Transformer with Gradient-Boosted Ranking

Panel: Evolution, Revolution, or Illusion? The Future of Python and Coding in the Age of AI

Pair & Share: How formal Mentoring pushed REWE Analytics to a new level

Open Table Formats in the Wild™ - Reloaded: Vortexing Ducks over Floating Icebergs

On Interventional Generalisation

Offline Fallback for a Mobile LoRaWAN Gateway

Octopus AutoML: Extracting Signal from Small and High-Dimensional Data

No, you can't 'eval' your way to fairness

Mastering the Hex: A Case Study in Reinforcement Learning for Strategy Games

Making bad CLIs fun with Small Language Models

Leveraging Hexagonal Architecture When Building Applications

Learnings Building DevOps as a Software Engineer

It Works on My Machine: Why LLM Apps Fail Users (Not Tests)

In Praise of Documentation: Tools, Tips & Techniques for Literate Programming in the AI Age

Hype, Hope, or Headache? Making Sense of GenAI, LLMs, and AI Agents with Anecdotal Evidence

How We Built an Inclusive Data Organization: Careers, Community & 50% Women

How to compare apples with oranges: Proper evaluation of article-level demand forecasts

"Honey, I vibe coded some crypto" - Security in the age of LLMS

Hierarchical Models in MMM: Can Structure beat data size?

Heat: scaling the Python scientific stack to HPC systems

From Ticket to Draft: How Munich Automates Citizen Inquiries with AI

From Scratch to Scale: Turning LLM Code into Architecture Insights

From Research Models to SLAs: Operationalizing TSFMs with Python

From Prompt to Production: How to use AI Code Assistants for Python Data Systems

From Pixel to Payouts: A Multi-Agent System for Real-Time Insurance Claims Processing

Foundation Models in Forecasting: Are We There Yet? Lessons from the Trenches

Escape the Hype: Teaching LLM Concepts Through an Interactive AI Factory Game

Empowering Data Scientists with Zero Platform Friction: Deploying Streamlit & Friends in 3 Minutes

Embedding Data Science in IoT devices with MicroPython and emlearn

Dynamic Knowledge Graphs

Don’t call your LLM too often! How to build your dialog graph with confidence and sleep at night.

Do you know how well your model is doing? Evaluate your LLMs

Destructive Testing: 10 Practical Ways to Expose Hidden Application Risks

Demystifying Agentic AI Using Small Language Models

Causal Inference through the lens of probabilistic programming

Catch the LLM if you Can: Watermarking LLMs

Building Secure Environments for CLI Code Agents

Building Non-Biased Synthetic Datasets: What Actually Works (and What Fails)

Building MCP at the Speed of Hype: Principles That Outlast the Trends

Building Agentic Systems with Python, LangGraph, MCP, and A2A

Beyond Vibe-Coding: A Practitioner's Guide to Spec-Driven Development in AI Engineering

Beyond Stateless: Why Your Web Service Architecture is Fighting Against Performance

Beyond Kafka and S3: Python Data Pipelines with HTTP-Native Bytestreams

Before You Ship Your Agent: An Agent Builder’s Primer on Jailbreaking Attacks

AI Is Changing the Game: Building Modular, AI-Ready Platforms on Top of Legacy Systems

AI Evals Done Right: From Vibes to Confident Decisions

Agent-Based Hyperparameter Optimization for Gradient Boosted Trees

Accuracy Is Overrated: Ship Stable Forecasts (Without Lying to Yourself)

Accelerate FastAPI Development with OpenAPI Generator

7 Anti-Lessons from Building a PydanticAI Agent: Mistakes We Made So You Don't Have To

5 Years of NiceGUI: What We Learned About Designing Pythonic UIs

Zero Code Change Acceleration: familiar interfaces and high performance ▶ Recording 📝 Transcript

What's inside the box? Building a deep learning framework from scratch. ▶ Recording 📝 Transcript

What do a tree and the human brain have in common-a not so serious introduction to digital pathology ▶ Recording 📝 Transcript