Click Fraud Detection in Online Advertising: A Comparative Study of Machine Learning Models
Zainab A. Abbas, Zahraa Mohammed Hilal, Hanan Ghali Jabbar · International Journal of Safety and Security Engineering · 2025
Advancements in networking and communication technologies have significantly boosted digital advertising, with global spending expected to reach $646 billion by 2024, including $495 billion from mobile internet. However, this growth is hindered by the persistent issue of click fraud, which leads to substantial financial losses and distorts advertising metrics. This study presents a comprehensive comparative analysis of multiple machine learning (ML) models including Random Forest, LightGBM, XGBoost, AdaBoost, Decision Tree, Gradient Boosting, and Multi-Layer Perceptron (MLP), for detecting click fraud in online advertising. A key novelty of this work lies in the integration of the LIME (Local Interpretable Model-agnostic Explanations) framework, which enhances transparency by interpreting the decision-making process of complex models. Through extensive data preprocessing and model evaluation using metrics such as accuracy, precision, recall, and F1-score, the Random Forest model achieved the highest accuracy of 95%, demonstrating robustness and generalization across different scenarios. Unlike prior studies, this research emphasizes model interpretability and trustworthiness, providing actionable insights for advertisers and platform designers. Comparative analysis with existing literature further highlights the methodological effectiveness and practical relevance of the proposed approach.