This repo performs matrix factorization using alternating least squares minimization to provide book recommendations. The implementation is based on the paper Matrix Factorization Techniques for Recommender Systems and draws on the corresponding CMU 10-315 course homework assignment. The data used in this project is a Goodreads book ratings dataset from UCSD Book Graph. The original dataset authors' papers are cited below.
Y. Koren, R. Bell and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems," in Computer, vol. 42, no. 8, pp. 30-37, Aug. 2009, doi: 10.1109/MC.2009.263.
Mengting Wan, Julian McAuley, "Item Recommendation on Monotonic Behavior Chains" , in RecSys'18.
Mengting Wan, Rishabh Misra, Ndapa Nakashole, Julian McAuley, "Fine-Grained Spoiler Detection from Large-Scale Review Corpora" , in ACL'19.
- Add bias consideration to matrix factorization
- Regularize loss function
- Expand dataset to include all genres
- Add frontend for getting specific recommendations