OpenMatch/TASTE
[CIKM 2023 Oral] This is the code repo for our CIKM‘23 paper "Text Matching Improves Sequential Recommendation by Reducing Popularity Biases".
This project helps e-commerce managers and content strategists create better product recommendations. It takes a history of user interactions with items (like purchases or views) and descriptive text for those items (like product descriptions) to generate a ranked list of relevant items. The goal is to provide recommendations that aren't just popular, but truly match a user's unique interests.
No commits in the last 6 months.
Use this if you need to improve recommendation systems by making them more personalized and less biased towards only popular items.
Not ideal if your recommendation system solely relies on collaborative filtering or if you lack detailed text descriptions for your items.
Stars
40
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/OpenMatch/TASTE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huangy22/NewsRecommender
A news recommendation system tailored for user communities
archd3sai/News-Articles-Recommendation
Objective of the project is to build a hybrid-filtering personalized news articles...
eugeneyan/recsys-nlp-graph
🛒 Simple recommender with matrix factorization, graph, and NLP. Beating the regular...
jonaylor89/WineInAMillion
Wine Recommender created with sentence-BERT and NearestNeighbor on AWS SageMaker
AmoliR/nlp-for-book-recommendation
Content based recommender system for books using NLP.