giacoballoccu/explanation-quality-recsys

Post Processing Explanations Paths in Path Reasoning Recommender Systems with Knowledge Graphs

40
/ 100
Emerging

This tool helps improve the quality of explanations generated by existing recommendation systems. If you already have a system that provides recommendations along with 'explanation paths' (like 'user liked movie X because it stars actor Y who also starred in Z, which user liked'), this tool takes those explanations as input. It then re-ranks them to make them more recent, popular, and diverse. The output is a refined set of explanations that are more helpful and fair for your users, ideal for product managers or data scientists working with recommendation engines.

No commits in the last 6 months.

Use this if you have a recommendation system that produces explanations and you want to enhance their quality, relevance, and fairness for your end-users without rebuilding your core recommender.

Not ideal if you are looking for a tool to build a recommendation system from scratch or if your current system does not generate path-based explanations.

recommender-systems explanation-quality personalization user-experience fairness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

35

Forks

11

Language

Python

License

GPL-2.0

Last pushed

Nov 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/giacoballoccu/explanation-quality-recsys"

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