A Simple and Robust Ensemble For Click-Through Rate Prediction

Xingmei Wang, Yankai Wang, Defu Lian

Abstract: This paper presents the strategy employed by the TOT team, which secured 3rd place in the ACM RecSys Challenge 2023 among academic teams. The challenge, orchestrated by ShareChat, focuses on online advertising and user privacy. The objective is to predict the probability of an application install for each anonymized entry. Our approach, though simple, proves efficient and comprises two primary components: initially, we explore state-of-the-art single-task and multi-task models, and subsequently, we integrate these via a simple yet robust ensemble.