Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204941,
        author = {Ms. Vaishali Balasaheb Pawar and Dr Ganesh Gorakhnath Taware},
        title = {Click fraud detection in online advertising using machine learning algorithms.},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4679-4687},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204941},
        abstract = {Internet advertising has turned out to be one of the main targets of click-fraud that causes significant losses to advertisers and a lack of confidence in the Internet tools. Fraudulent clicks are usually created by automated bots, scripts, or organized human resources to create fraudulent ad clicks or deplete competition's advertising budgets. The likelihood of fraud, by its scale, complexity, and dynamism, is making traditional rule-based detection systems less effective. This has led machine learning techniques to be an appealing approach for identifying abnormal click behavior in large volumes of advertising data. This paper presents two machine learning methods for identifying fake clicks on an advertisement: a support vector machine (SVM) and a k-nearest neighbors (KNN) classifier. The process includes data cleaning, feature generation, data balancing using the synthetic minority oversampling technique (SMOTE), and training models on the processed data. Accuracy, precision, recall, and F1-score are used to compare models, and cross-validation is employed to ensure reproducibility. The findings indicate that SVM and KNN are both useful in the process of distinguishing actual clicks and fraudulence, which can be used as a reliable baseline on which a click fraud detection system is based. The results highlight the importance of proper data preprocessing, balanced data, and model testing in fraud detection. The method will help build more viable and scalable fraud-detection systems for the digital advertising platform.},
        keywords = {click fraud detection, online advertising, machine learning, support vector machine, K-nearest neighbors, SMOTE, fraud analytics, and digital advertising security.},
        month = {June},
        }