Computer Science

CLC number: TP183

A Lambda Layer-Based Convolutional Sequence Embedding Model for Click-Through Rate Prediction

¹ Tenth Research Institute, China Electronics Technology Group Corporation, Chengdu 610000, Sichuan, China
² Department of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, Jiangsu, China
³ Research Institution of Information Technology, Tsinghua University, Beijing 100084, China
⁴ School of Computer Science, Wuhan University, Wuhan 430072, Hubei, China

^† Corresponding author. E-mail: gfzhou@whu.edu.cn

Received: 29 December 2023

Abstract

In the era of intelligent economy, the click-through rate (CTR) prediction system can evaluate massive service information based on user historical information, and screen out the products that are most likely to be favored by users, thus realizing customized push of information and achieve the ultimate goal of improving economic benefits. Sequence modeling is one of the main research directions of CTR prediction models based on deep learning. The user's general interest hidden in the entire click history and the short-term interest hidden in the recent click behaviors have different influences on the CTR prediction results, which are highly important. In terms of capturing the user's general interest, existing models paid more attention to the relationships between item embedding vectors (point-level), while ignoring the relationships between elements in item embedding vectors (union-level). The Lambda layer-based Convolutional Sequence Embedding (LCSE) model proposed in this paper uses the Lambda layer to capture features from click history through weight distribution, and uses horizontal and vertical filters on this basis to learn the user's general preferences from union-level and point-level. In addition, we also incorporate the user's short-term preferences captured by the embedding-based convolutional model to further improve the prediction results. The AUC (Area Under Curve) values of the LCSE model on the datasets Electronic, Movie & TV and MovieLens are 0.870 7, 0.903 6 and 0.946 7, improving 0.45%, 0.36% and 0.07% over the Caser model, proving the effectiveness of our proposed model.