Wide & Deep Learning for Recommender Systems
Abstract
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more feature engineering effort. With less feature engineering, deep neural networks can generalize better to unseen feature combinations through low-dimensional dense embeddings learned for the sparse features. However, deep neural networks with embeddings can over-generalize and recommend less relevant items when the user-item interactions are sparse and high-rank. In this paper, we present Wide & Deep learning---jointly trained wide linear models and deep neural networks---to combine the benefits of memorization and generalization for recommender systems. We productionized and evaluated the system on Google Play, a commercial mobile app store with over one billion active users and over one million apps. Online experiment results show that Wide & Deep significantly increased app acquisitions compared with wide-only and deep-only models. We have also open-sourced our implementation in TensorFlow.
Cite
@article{arxiv.1606.07792,
title = {Wide & Deep Learning for Recommender Systems},
author = {Heng-Tze Cheng and Levent Koc and Jeremiah Harmsen and Tal Shaked and Tushar Chandra and Hrishi Aradhye and Glen Anderson and Greg Corrado and Wei Chai and Mustafa Ispir and Rohan Anil and Zakaria Haque and Lichan Hong and Vihan Jain and Xiaobing Liu and Hemal Shah},
journal= {arXiv preprint arXiv:1606.07792},
year = {2016}
}