A scalable two-stage news recommender that retrieves relevant candidates and reranks them using hybrid lexical and semantic features to optimize top-K recommendation quality.
-
Updated
Jan 16, 2026 - Jupyter Notebook
A scalable two-stage news recommender that retrieves relevant candidates and reranks them using hybrid lexical and semantic features to optimize top-K recommendation quality.
Contains Oria's (Erel's student) ranking project (see sklearn/ranking). Nov 2024
This project implements and evaluates ENSFM for recommendation systems on modern, large-scale e-commerce datasets. The research focuses on assessing the scalability, efficiency, and accuracy of ENSFM when applied to real-world datasets from Amazon Books and Yelp
Add a description, image, and links to the ndcg-ranking topic page so that developers can more easily learn about it.
To associate your repository with the ndcg-ranking topic, visit your repo's landing page and select "manage topics."