yandex-research/tabred

(ICLR 2025 Spotlight) TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks

35
/ 100
Emerging

This project helps data scientists, machine learning engineers, and researchers assess how well their machine learning models perform on real-world business problems. It provides a collection of industrial-grade tabular datasets, often with time-evolving data, allowing you to evaluate your model's accuracy and robustness on data that mirrors production environments, rather than traditional academic benchmarks. You feed in your machine learning models and get back insights into their true performance.

No commits in the last 6 months.

Use this if you need to rigorously test your tabular machine learning models on realistic, time-evolving business data to understand their real-world applicability.

Not ideal if you are looking for new model architectures or a framework to deploy models, rather than a benchmark for existing methods.

predictive-modeling risk-assessment customer-conversion delivery-optimization housing-market-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

90

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Jun 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yandex-research/tabred"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.