xuetf/KDD_CUP_2020_Debiasing_Rush

Solution to the Debiasing Track of KDD CUP 2020

39
/ 100
Emerging

This project provides a solution for improving recommendation systems by reducing bias. It takes in user clickstream data and item features, then generates a refined list of recommended items. E-commerce managers, content platform strategists, or anyone managing a recommendation engine would use this to ensure a fairer and more diverse user experience.

160 stars. No commits in the last 6 months.

Use this if your recommendation system suffers from popularity bias, where only frequently clicked items are suggested, neglecting valuable, less-exposed content.

Not ideal if you're looking for a simple plug-and-play recommendation system without custom data processing or if your data isn't in a clickstream format.

e-commerce content-recommendation personalization bias-mitigation user-engagement
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

160

Forks

38

Language

Jupyter Notebook

License

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xuetf/KDD_CUP_2020_Debiasing_Rush"

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