DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

13 Mar 2017Huifeng GuoRuiming TangYunming YeZhenguo LiXiuqiang He

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise feature engineering... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Click-Through Rate Prediction Amazon DeepFM AUC 0.8683 # 3
Click-Through Rate Prediction Bing News DeepFM AUC 0.8376 # 3
Click-Through Rate Prediction Bing News DeepFM Log Loss 0.2671 # 3
Click-Through Rate Prediction Company* DeepFM AUC 0.8715 # 1
Click-Through Rate Prediction Company* DeepFM Log Loss 0.02618 # 1
Click-Through Rate Prediction Criteo DeepFM AUC 0.8007 # 2
Click-Through Rate Prediction Criteo DeepFM Log Loss 0.45083 # 3
Click-Through Rate Prediction Dianping DeepFM AUC 0.8481 # 2
Click-Through Rate Prediction Dianping DeepFM Log Loss 0.3333 # 2
Click-Through Rate Prediction MovieLens 20M DeepFM AUC 0.7324 # 3