DDIN: Deep Disentangled Interest Network for Click-Through Rate Prediction

Click-Through Rate(CTR) prediction aims to predict the possibility of users clicking on products, which has become the core task of advertising recommendation systems. Due to the richness of user historical behavior, a key to making effective prediction is to capture users' diverse interests from historical behavior. An efficient way to do this is to perform dot product of behavior and target embedding with attentive neural networks. To better model the users' diverse interests, our proposed disentangled interest extraction block decouples the unary terms modeling the impact of user behavior sequence from pairwise interactions. Specifically, the decoupled pairwise term can learn the pure pairwise interactions, whereas the unary term models the impact of behavior sequence on each target items. Meanwhile, our model emphasizes both high- and low-order feature interactions by combining Attentional Factorization Machines(AFMs) with deep learning. This work intends to accomplish our goal by proposing a novel architecture Deep Disentangled Interest Network(DDIN). We conduct comprehensive experiments on Movielens dataset and Amazon electronic dataset. The results demonstrate the effectiveness of DDIN which is superior to some state-of-art models by up to 26.271 %.

I. Introduction

Click-Through Rate(CTR) prediction plays an essential role in advertising industry, which a lot of researchers pay much attention to in the past decade. The data in the sphere of CTR are typically multi -categorical feature expression [1]–[4]. The general way to cope with multi -categorical data is transforming the data into binary features via one-hot or multi-hot encoding. Recently, deep learning based methods have been blooming [1]–[3], [5], [6], which utilized embedding layer to map large-scale and sparse input features into low-dimensional and dense embedding vectors. They all followed the structure named Embedding&MLP.