Machine Learning & Deep Learning & Statistics
15 talks from the 2026 edition.
-
Accuracy Is Overrated: Ship Stable Forecasts (Without Lying to Yourself) ▶ Recording 📝 Transcript
Illia Babounikau
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...
-
Agent-Based Hyperparameter Optimization for Gradient Boosted Trees ▶ Recording 📝 Transcript
Huijo Kim
### 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...
-
Causal Inference through the lens of probabilistic programming ▶ Recording 📝 Transcript
Dr. Juan Orduz
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,...
-
Hierarchical Models in MMM: Can Structure beat data size? ▶ Recording 📝 Transcript
Mohamed Amine Jebari
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...
-
How to compare apples with oranges: Proper evaluation of article-level demand forecasts ▶ Recording 📝 Transcript
Stefan Birr, Mones Raslan
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...
-
Mastering the Hex: A Case Study in Reinforcement Learning for Strategy Games ▶ Recording 📝 Transcript
Simon Hedrich
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...
-
Octopus AutoML: Extracting Signal from Small and High-Dimensional Data ▶ Recording 📝 Transcript
Nils Haase, Andreas Wurl
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...
-
On Interventional Generalisation ▶ Recording 📝 Transcript
Andy Kitchen
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...
-
Personalized Restaurant Recommendations at Scale combining Transformer with Gradient-Boosted Ranking ▶ Recording 📝 Transcript
Marcel Kurovski, Steffen Klempau
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...
-
Restaurants around train stations are bad and I can prove it ▶ Recording 📝 Transcript
Dennis Schulz
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,...
-
Solving Marketplace Cold Start at Scale with Ranking ▶ Recording 📝 Transcript
Theodore Meynard
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...
-
The Art of the Optimal: A Pythonic Approach to Complex Decision-Making ▶ Recording 📝 Transcript
Justine Broihan
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...
-
The foundation model revolution for tabular data ▶ Recording 📝 Transcript
Frank Hutter
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...
-
Using Sensor Fusion and ML to Navigate Underground When GPS Fails ▶ Recording 📝 Transcript
Étienne Tremblay
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...
-
When Space Weather Breaks Your GPS: Building an Explainable Early Warning System ▶ Recording 📝 Transcript
Vincenzo Ventriglia
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...