DeepCTR is a Easy-to-use,Modular and Extendible package of deep-learning based CTR models along with lots of core components layers which can be used to easily build custom models. You can use any complex model with model.fit(), and model.predict(). Provide tf.keras.Model like interface for quick experiment. Provide tensorflow estimator interface for large scale data and distributed training. It is compatible with both tf 1.x and tf 2.x. With the great success of deep learning,DNN-based techniques have been widely used in CTR prediction task. The data in CTR estimation task usually includes high sparse,high cardinality categorical features and some dense numerical features. Since DNN are good at handling dense numerical features,we usually map the sparse categorical features to dense numerical through embedding technique.
Features
- CCPM (Convolutional Click Prediction Model)
- PNN (Product-based Neural Network)
- FNN (Factorization-supported Neural Network)
- MLR(Mixed Logistic Regression/Piece-wise Linear Model)
- NFM (Neural Factorization Machine)
- DCN (Deep & Cross Network)