The EffectiveCtr library offers state-of-the-art algorithms for [deep learning recommendation]. EffectiveCtr is built on latest [TensorFlow 2][(https://tensorflow.org/)] and designed with modular structure， making it easy to discover patterns and answer questions about tabular-structed data.
The main goals of EffectiveCtr:
Easy to use, newbies can get hands dirty with deep learning quickly Good performance with web-scale data Easy to extend, Modular architecture let you build your Neural network like playing LEGO! Let's Get Started!
Titile Booktitle Resources
FM: Factorization Machines ICDM'2010
FFM: Field-aware Factorization Machines for CTR Prediction RecSys'2016
FNN: Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction ECIR'2016
PNN: Product-based Neural Networks for User Response Prediction ICDM'2016
Wide&Deep: Wide & Deep Learning for Recommender Systems DLRS'2016
AFM: Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks IJCAI'2017
NFM: Neural Factorization Machines for Sparse Predictive Analytics SIGIR'2017
DeepFM: DeepFM: A Factorization-Machine based Neural Network for CTR Prediction[C] IJCAI'2017
DCN: Deep & Cross Network for Ad Click Predictions ADKDD'2017
xDeepFM: xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems KDD'2018
DIN: Deep Interest Network for Click-Through Rate Prediction KDD'2018
DIEN: Deep Interest Evolution Network for Click-Through Rate Prediction AAAI'2019
DSIN: Deep Session Interest Network for Click-Through Rate Prediction IJCAI'2019
AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks CIKM'2019
FLEN: Leveraging Field for Scalable CTR Prediction AAAI'2020
DFN: Deep Feedback Network for Recommendation IJCAI'2020
https://github.com/shenweichen/DeepCTR