The course on recommender systems conducted in National Research University - Higher School of Economics (Moscow, Russia). Academic year 2021-2022.
Course on recommender systems.
- Examples of RecSys models in production.
- Formalization of the ranking (recommender systems) task (2 popular types of tasks, 2 types of data sets).
- Ranking functions (BPR, WARP, RankNET, LambdaRank, LambdaMART).
- Metrics for the quality estimation (Hitrate, Precision @ k, Recall @ k, AP@k, MAP@l, DCG@k, NDCG@k).
- Taxonomy of RecSys approaches ([MF, FM, CF & other general], Content-based [including knowledge graph based, GB for ranking], Context-based, Sequential based, RL, Hybrid [including two-level cascade, blending]).
- Pros / Cons of current approaches.
- Review of the main future directions.
- Problems of the current articles.
- Recommended sources on RecSys.
- Basic baselines
- Item-based and user-based similarity, similarity metrics.
- Matrix Factorization (SVD et al.)
- Collaborative Filtering (ALS)
- Content-based & Hybrid recommenders taxonomy
- LightFM model and library
- Example of cascade recommender model (using gradient boosting on the second level)
- Important preprocessing steps
- Cross-validation types for recommender systems