A reproducible, data-centric benchmarking framework evaluating the robustness of tabular machine learning models under systematic feature shift using OpenML-CC18 datasets and automated feature engineering.
benchmarking automated-feature-engineering wilcoxon-test data-centric-ai distribution-shift model-reliability tabular-machine-learning feature-shift openml-cc18 wilcoxon-signed-rank-test
-
Updated
Apr 13, 2026 - Python