Improving Internet Advertising Using Click – Through Rate Prediction

Abstract

Online advertising is a billion-dollar industry, with many companies choosing online websites and various social media platforms to promote their products. The primary concerns in online marketing are to optimize the performance of a digital advert, reach the right audience, and maximize revenue, which can be achieved by predicting the accurate probability of a given ad being clicked, called the Click-Through Rate. It is assumed that a high CTR depicts the ad reaching its target customers while a low CTR shows that it is not reaching its desired audience, which may constitute a low return on investment (ROI). We propose a data-science-driven approach to help businesses improve their internet advertising campaigns which involves building various machine learning models to accurately predict the CTR and selecting the best-performing model. To build our classification models, we use the Avazu dataset, publicly available on the Kaggle website. Having insights on this metric will allow companies to compete in real-time bidding, gauge how relevant their keywords are in search engine querying, and mitigate an unexpected loss in spending budget. The authors in this paper strive to use modern machine learning tools and techniques to improve the performance of predicting Click-Through Rate (CTR) in online advertisements and bring change to the industry.

Keywords: online advertising, machine learning random forest, click, through rate

DOI: 10.54941/ahfe1003772