RecSys

Why we included this project

This is a curated reading list for recommender systems and computational advertising, not a tool you install and run. The value is in how the material is organized: classic statistical models like LR, FFM, and GBDT sit alongside deep learning approaches such as FM, DeepFM, and DeepCTR, with pointers to libraries like LightGBM, XGBoost, and xLearn. Sections on competitions, blogs, and classic papers let a newcomer follow a path from theory to practice, and references to real contests like Criteo and Avazu ground the concepts in actual problems. Data scientists and ML engineers looking to brush up on CTR and CVR prediction will find a handy map to the literature and code worth reading.