This repository contains the code for the Recommender System Challenge 2023, made on Kaggle.
The challenge involves recommending to users 10 books that are most likely to interact with.
The final recommender used in the challenge was an hybrid of:
- SLIM Elastic Net
- RP3beta
obtained merging the two similarity matrices using a weighted sum.
We trained all the models using both kaggle and colab notebooks.
The evaluation metric used for the competition is MAP@10
- Public leaderboard score: 0.14042 (18th/63)
- Private leaderboard score: 0.13984 (20th/63)
For this challenge it was used the code taken from the course repository, that provides recommenders and utility code.