Systematic Literature Review on Click Through Rate Prediction

Abstract

The ability to anticipate whether a user will click on an item is one of the most crucial aspects of operating an e-commerce business, and clickthrough rate prediction is an attempt to provide an answer to this question. Beginning with the simplest multilayer perceptrons and progressing to the most sophisticated attention networks, researchers employ a variety of methods to solve this issue. In this paper, we present the findings of a comprehensive literature review that will assist researchers in getting a head start on developing new solutions. The most prevalent models were variants of the state-of-the-art DeepFM model.