EasyRec: An Easy-to-Use, Extendable and Efficient Framework for Building Industrial Recommendation Systems

We present EasyRec, an easy-to-use, extendable and efficient recommendation framework for building industrial recommendation systems. Our EasyRec framework is superior in the following aspects:first, EasyRec adopts a modular and pluggable design pattern to reduce the efforts to build custom models; second, EasyRec implements hyper-parameter optimization and feature selection algorithms to improve model performance automatically; third, EasyRec applies online learning to adapt to the ever-changing data distribution. The code is released: https://github.com/alibaba/EasyRec.

Authors

• Mengli Cheng Alibaba Group
• Yue Gao
• Guoqiang Liu Alibaba Group
• HongSheng Jin Alibaba Group

Keywords

• Distributed Training
• Hyperparameter Optimization
• Large Scale
• Recommedation Framework