kang205/SASRec

SASRec: Self-Attentive Sequential Recommendation

51
/ 100
Established

This project helps e-commerce managers, content strategists, or product owners understand what items a user will likely interact with next, based on their past actions. It takes a history of user interactions with items (like products viewed or videos watched) and outputs a ranked list of recommendations for future items. The end-user persona is anyone responsible for improving personalized user experiences on a platform.

948 stars. No commits in the last 6 months.

Use this if you need to predict the next item a user will engage with, given their sequence of past interactions, to improve recommendation systems.

Not ideal if you are looking for a system that recommends items based on broad user categories or item similarities rather than specific sequential behavior.

e-commerce recommendations content personalization sequential user behavior product discovery user engagement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

948

Forks

181

Language

Python

License

Apache-2.0

Last pushed

Aug 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kang205/SASRec"

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