cnkuangshi/LightCTR

Lightweight and Scalable framework that combines mainstream algorithms of Click-Through-Rate prediction based computational DAG, philosophy of Parameter Server and Ring-AllReduce collective communication.

51
/ 100
Established

LightCTR helps online businesses and e-commerce platforms improve how they predict user engagement. It takes raw user behavior data, click logs, and content information, then processes it to output highly accurate predictions of whether a user will click on an ad or product. This is designed for data scientists, machine learning engineers, and analysts working on large-scale recommendation systems or online advertising.

671 stars. No commits in the last 6 months.

Use this if you need a scalable and lightweight framework to build and train sophisticated click-through rate prediction models on massive, sparse datasets, especially in distributed environments.

Not ideal if you're looking for a general-purpose machine learning library for small datasets or if you don't require high-performance distributed training specific to CTR prediction.

click-through-rate-prediction online-advertising recommendation-systems e-commerce user-behavior-analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

671

Forks

139

Language

C++

License

Apache-2.0

Last pushed

Jun 17, 2019

Commits (30d)

0

Get this data via API

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

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