Evgeny Frolov

polara. Recommender system and evaluation framework for top-n recommendations tasks that respects polarity of feedbacks. Fast, flexible and easy to use. Written in python, boosted by scientific python stack.

ipypb. Python progress bar with rich output that uses native ipython functionality. Widget-free. Works even in JupyterLab.

HyperbolicRecommenders. Accompanying code for the paper Performance of Hyperbolic Geometry Models on Top-N Recommendation Tasks, accepted at ACM RecSys 2020.

fifty-shades. Source code to support ACM RecSys'16 paper "Fifty Shades of Ratings: How to Benefit from a Negative Feedback in Top-N Recommendations Tasks"

TensorGlue. Tensor-based recommender system that incorporates categorical contextual information into collaborative filtering workflow.

recsys19_hybridsvd. Accompanying code for reproducing experiments from the HybridSVD paper. Preprint is available at https://arxiv.org/abs/1802.06398.

RecSys_ISP2017. ISP Course at Skoltech

acaml2018_recsys. Jupyter Notebook

Stable_Recommendations. The accompanying code for our paper.

hybridsvd. Supplementary materials to reproduce experiments

cofida. Fast in-memory pytorch dataloaders designed specifically for collaborative filtering data.

RecSysLeaderboardApp. JavaScript