Deep Interest Evolution Network for Click-Through Rate Prediction (2018-09-11T00:00:00.000000Z)

TL;DR

This paper proposes a novel model, named Deep Interest Evolution Network~(DIEN), for CTR prediction, which significantly outperforms the state-of-the-art solutions and design interest extractor layer to capture temporal interests from history behavior sequence.

Abstract

Click-through rate (CTR) prediction, whose goal is to estimate the probability of a user clicking on the item, has become one of the core tasks in the advertising system. For CTR prediction model, it is necessary to capture the latent user interest behind the user behavior data. Besides, considering the changing of the external environment and the internal cognition, user interest evolves over time dynamically. There are several CTR prediction methods for interest modeling, while most of them regard the representation of behavior as the interest directly, and lack specially modeling for latent interest behind the concrete behavior. Moreover, little work considers the changing trend of the interest. In this paper, we propose a novel model, named Deep Interest Evolution Network (DIEN), for CTR prediction. Specifically, we design interest extractor layer to capture temporal interests from history behavior sequence. At this layer, we introduce an auxiliary loss to supervise interest extracting at each step. As user interests are diverse, especially in the e-commerce system, we propose interest evolving layer to capture interest evolving process that is relative to the target item. At interest evolving layer, attention mechanism is embedded into the sequential structure novelly, and the effects of relative interests are strengthened during interest evolution. In the experiments on both public and industrial datasets, DIEN significantly outperforms the state-of-the-art solutions. Notably, DIEN has been deployed in the display advertisement system of Taobao, and obtained 20.7% improvement on CTR.

Deep Interest Evolution Network for Click-Through Rate Prediction

TL;DR

Abstract

Authors

References26 items

Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising

Improving Native Ads CTR Prediction by Large Scale Event Embedding and Recurrent Networks

xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems

ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation

Rocket Launching: A Universal and Efficient Framework for Training Well-performing Light Net

Deep Interest Network for Click-Through Rate Prediction

Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

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

Product-Based Neural Networks for User Response Prediction

A Dynamic Recurrent Model for Next Basket Recommendation

Multi-Rate Deep Learning for Temporal Recommendation

Wide & Deep Learning for Recommender Systems

Dynamic Memory Networks for Visual and Textual Question Answering

Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering

Image-Based Recommendations on Styles and Substitutes

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Principal Component Analysis (PCA)

Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks

Kernel Fusion: An Effective Method for Better Power Efficiency on Multithreaded GPU

Factorization Machines

BPR: Bayesian Personalized Ranking from Implicit Feedback

Greedy function approximation: A gradient boosting machine.

Long Short-Term Memory

and Karatzoglou

and McAuley

and Schmidhuber

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names