Hirosora LightCTR Save

LightCTR is a tensorflow 2.0 based, extensible toolbox for building CTR/CVR predicting models.

Project README

LightCTR

LightCTR is a tensorflow 2.0 based, extensible toolbox for building CTR/CVR predicting models. It provides several off-the-shelf popular CTR models for you to use. And it also contains some useful model blocks to help you build your own model quickly.

Have a quick start with the example script ./examples/ctr_predict.py

A small example dataset avazu_1w.txt is provided in ./datasets, It is sampled from a kaggle dataset with 10000 rows.

Models List

Model Paper
Factorization-supported Neural Network (FNN) [ECIR 2016]Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction
Product-based Neural Network (PNN) [ICDM 2016]Product-based neural networks for user response prediction
Wide & Deep [DLRS 2016]Wide & Deep Learning for Recommender Systems
DeepFM [IJCAI 2017]DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
Deep & Cross Network (DCN) [ADKDD 2017]Deep & Cross Network for Ad Click Predictions
xDeepFM [KDD 2018]xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
Neural Factorization Machine (NFM) [SIGIR 2017]Neural Factorization Machines for Sparse Predictive Analytics
Attentional Factorization Machine (AFM) [IJCAI 2017]Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
AutoInt [arxiv 2018]AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
Convolutional Click Prediction Model (CCPM) [CIKM 2015]A Convolutional Click Prediction Model
Feature Generation by Convolutional Neural Network (FGCNN) [WWW 2019]Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
Mixed Logistic Regression (MLR) [arxiv 2017]Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
FiBiNET [RecSys 2019]FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
NFFM [arxiv 2019]Operation-aware Neural Networks for User Response Prediction
Open Source Agenda is not affiliated with "Hirosora LightCTR" Project. README Source: Hirosora/LightCTR

Open Source Agenda Badge

Open Source Agenda Rating