DataFunTalk
Dec 20, 2019 · Artificial Intelligence
AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
The article presents AutoCross, a system that automatically generates and selects high‑order feature crossings for tabular data using multi‑granularity discretization, beam search, field‑wise logistic regression and successive mini‑batch gradient descent, achieving superior accuracy and efficiency in large‑scale recommendation scenarios.
AutoCrossRecommendation systemsautomatic feature engineering
0 likes · 10 min read