Skip to content

sunil22516/RecomSystems_NMFV3

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NeuMf and MF

This project implements a recommendation system using both Matrix Factorization (SVD/ALS) and a deep learning approach, Neural Collaborative Filtering (NeuMF), to predict user-item interactions. The dataset is preprocessed by binarizing ratings, and the models are trained to learn user and item representations for ranking tasks. Additionally, an LLM-based method is included to generate ratings as part of the project requirements.

The performance of the models is evaluated using Hit Rate and NDCG, focusing on ranking quality rather than raw prediction accuracy. The pipeline includes data preprocessing, model training, prediction generation, and ranking-based evaluation, with results presented in tabular form for comparison across different approaches.

About

NeuMF-based movie recommender trained on implicit (binarized) feedback to generate Top-K recommendations. Includes LLM-inspired semantic reranking

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Packages

 
 
 

Contributors