User Response Prediction in Online Advertising

Abstract

Online advertising, as the vast market, has gained significant attentions in various platforms ranging from search engines, third-party websites, social media, and mobile apps. The prosperity of online campaigns is a challenge in online marketing and is usually evaluated by user response through different metrics, such as clicks on advertisement (ad) creatives, subscriptions to products, purchases of items, or explicit user feedback through online surveys. Recent years have witnessed a significant increase in the number of studies using computational approaches, including machine learning methods, for user response prediction. However, existing literature mainly focuses on algorithmic-driven designs to solve specific challenges, and no comprehensive review exists to answer many important questions. What are the parties involved in the online digital advertising eco-systems? What type of data are available for user response prediction? How to predict user response in a reliable and/or transparent way? In this survey, we provide a comprehensive review of user response prediction in online advertising and related recommender applications. Our essential goal is to provide a thorough understanding of online advertising platforms, stakeholders, data availability, and typical ways of user response prediction. We propose a taxonomy to categorize state-of-the-art user response prediction methods, primarily focus on the current progress of machine learning methods used in different online platforms. In addition, we also review applications of user response prediction, benchmark datasets, and open-source codes in the field.

Click-through rate prediction in online advertising: A literature review

“…Second, we identify current research trends, main challenges and potential future directions worthy of further explorations. This review complements review articles recently published on users' responses (including CTR, conversion rate and user engagement) prediction (Gharibshah and Zhu, 2021) and CTR prediction (Wang, 2020;Zhang et al, 2021a). More specifically, Gharibshah and Zhu (2021) focused on online advertising platforms, data sources and features, and typical methods for user response prediction; Wang (2020) briefly introduced several classical methods for CTR prediction; and Zhang et al (2021a) concentrated on the transfer from shallow to deep learning models for CTR prediction, explicit feature interaction modules and automated methods for architecture design.…”

“…In the following we go through three major FM-based modeling frameworks, namely, the classic Factorization Machines (FMs), Field-aware Factorization Machines (FFMs) and Field-weighted Factorization Machines (FwFMs). Among the three FMs-based modeling frameworks, FMs emphasize feature interactions, while FFMs consider both feature interactions and field interactions, and FwFMs are an improved combination of FMs and FFMs (Gharibshah & Zhu, 2021;Juan et al, 2016;Juan et al, 2017;Pan et al, 2018;.…”

“…Advertising data usually contain a large number of categorical features which need binary representation, resulting in high dimensional vectors with many zero elements (Gharibshah & Zhu, 2021). This raises the data sparsity problem for CTR prediction.…”