Ad Click-Through Rate Prediction: A Comparative Study of Machine Learning Models

Authors:

Abstract
Billions of dollars are spent annually on internet advertisements in our world. It promotes awareness-building, increases website traffic, and persuades the intended audience to act, such as making a purchase. It is among the best strategies for growing the consumer base and communicating marketing and promotional messaging. CTR is a crucial measure since it provides you with valuable insights into your customers and what strategies work and don’t when it comes to reaching your target market. This research explores the effectiveness of diverse classification algorithms for predicting ad click-through rates (CTR). Using a comprehensive dataset with key features, including daily time spent on the site, daily internet usage, age, and area income, we evaluated nine classification models. The study provides actionable insights for marketers, emphasizing the importance of algorithm selection in optimizing ad campaigns. We observed that XGBoost gives a maximum accuracy of 0.7885 and a maximum AUC-ROC of 0.8778 [1].

This publication has 13 references indexed in Scilit: