faizanahemad/Hybrid-Weighted-Embedding-Recommender

A Hybrid Recommendation system which uses Content embeddings and augments them with collaborative features. Weighted Combination of embeddings enables solving cold start with fast training and serving

35
/ 100
Emerging

This project helps e-commerce stores, streaming services, or content platforms provide personalized suggestions to their users. It takes in information about items (like movie genres or product descriptions) and user interactions (like past purchases or ratings) to suggest relevant new items. This is useful for anyone managing a platform where recommending items to users is key to engagement and sales.

No commits in the last 6 months.

Use this if you need a recommendation system that can effectively suggest items even to new users or for new products, by intelligently combining item details with user behavior.

Not ideal if your recommendation needs are simple and you don't have detailed content information for your items, or if you prefer a system that focuses purely on collaborative filtering without leveraging item attributes.

e-commerce content-discovery personalization customer-engagement product-recommendation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

17

Forks

3

Language

Python

License

MIT

Last pushed

Dec 08, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/faizanahemad/Hybrid-Weighted-Embedding-Recommender"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.