PyData Amsterdam 2026, September 10 & 11

Explore the selected talks, deep-dives and tutorials, the full program schedule will be published soon.

Get your early bird tickets

Talks

When one score is not enough: matching real-world groundwater time series at scale

Luisa Orozco

The A/B Testing Blind Spot: Solving the Opt-In Paradox with Randomized Encouragement and DoubleML

Lin Jia & Kexin Fei

Beyond Benchmarks: Optimizing LLMs and Puzzle Agents for Cryptic Crosswords

Pauline van Nies

DuckDB + ADBC: Faster, Easier Data Analytics

Matt Topol

Distilling LLMs into Classical ML for 5,000+ Classes

Oz Mendelsohn

Your dashboard is too late: Building real-time KPI alerting systems with Python

Thijs Bressers

DuckLake: The Lakehouse That Finally Embraces the Database

Graziano Montanaro

Scheduling at Scale: Building a Railway Timetable Optimizer in Python

Willem Feijen

Inside the Mind of an LLM

Luca Baggi

Scaling Two-Way Fixed Effects Models in Python with pyfixest: Lessons from Airline Pricing

Rutger Lit

Amidst the Visualization and Art of Data

Nadieh Bremer

When Should AI Speak? Letting Agents Decide When It's Their Turn

Emir Can & Anna Pillar

Systems for Scale: Architecting a Nationwide Energy Forecasting Platform

Mohit

The unreasonable effectiveness of DAS: ML on fiber-optic vibration data for rail monitoring

Schelto Crone & Joost van 't Schip

LLMs on a Diet: Low-bit pretraining at scale with FP8

Arkadii

No GIL, Real Gains: Porting a C++ Python Extension to Free-Threaded Python 3.14

Auxten Wang

Beyond the Holdout: Mitigating Censorship Bias with Asymmetric IPW

Leonardo Amorim

Maybe 3 Minutes, Maybe Chaos – when Conformal Prediction meets my commuting life

Konstantinos Tsoumas

Modernizing Spark: Performance Boost without Rewrite

Shehab Amin & Santosh Pingale

From Query to Discovery: Building an AI Agent That Helps Travelers Explore

Giampaolo Casolla & Steven Mi

Data First, Model Second: Three Strategies for Production Computer Vision

Alexander Kern &.Guus van der Ham

When RAG is not enough: Architecting for 10M+ context windows

Azamat Omuraliev

Trillion-Token Pretraining: Building a Foundational Model for payment data

Hanna van der Vlis & Martin Iglesias Goyanes

Your A/B Test Is Leaking: Practical Lessons in Measuring Network Effects

Dror A. Guldin

Embed First, Predict Later: Energy forecasting from weather embeddings

Kai Jeggle

Real-time vs Batch Features for ML: Lessons from Fraud Detection at Scale

Csanád Bakos

From LLMs to Agents and from words to actions

Maarten Grootendorst & Jay Alammar

Agent-Friendly Data Platforms: Semantic Layers, Tool APIs, and Guardrails for Agentic

Borja Enrique Vilar Martos

Evaluating Agents at Scale: From 50 Examples to a Production Flywheel

Bauke Brenninkmeijer

A short tour of forgotten Machine Learning algorithms

Christiaan Erdbrink

The New Polars Engine That Tackles Megabyte to Terabyte Workloads

Thijs Nieuwdorp

Cold Start at Scale: Three Years of Experiments in a Travel Marketplace

Theodore Meynard

The Context Trap: Addressing Item Neglect and Calibration in Deep Point-Wise Rankers

Belle Bruinsma, Akhila Vangara, Laura Israel

Deterministic Orchestration for ML Experiments with Coding Agents

Oleh Kostromin & Iryna Kondrashchenko

Enhance: Feeding the World with Data through Multi-Objective Optimization

Marijn Markus

Serving Personalized ML at Scale with Evolving Runtimes

Rayan Daod

The Art of Forgetting: A Compress-Retrieve Pattern for Long-Context LLMs

Arian Pasquali

Is Your Agent as Secure as You Think?

Marysia Winkels

When Context Breaks: Recursive Language Models with DSPy

Niels van Galen Last

Get your tickets

Keynote speakers 2026

  • This is an image of Jay Alammar.

    Jay Alammar

    Director & Engineering Fellow @ Cohere

    Joint keynote: "From LLMs to Agents and from Words to Actions"

  • An image of Maarten Grootendorst.

    Maarten Grootendorst

    Developer Relations Engineer @ Google DeepMind

    Joint keynote: "From LLMs to Agents and from Words to Actions"

  • An image of Laura Summers

    Laura Summers

    Lead Design Engineer @ Pydantic

    Keynote title: TBD

  • Nadieh Bremer

    Data Visualization Designer @ Visual Cinnamon

    Keynote title: Amidst the Visualization and Art of Data

Get your tickets

Note to all speakers: if you require a speaker adjustment due to exceptional circumstances, such as illness, visa issues or other unavoidable events, please make a request for approval via the organizing committee at amsterdam@pydata.org.