Smart Guard: A Comprehensive Approach to Ad Click Fraud Detection

Akash Vir; Dr. Shivam Upadhyay

doi:10.32628/CSEIT2410612403

Authors

Akash Vir Department of Computer Science & Engineering, Krishna School of Technology, Drs. Kiran & Pallavi Patel Global University, Vadodara, Gujarat, India Author
Dr. Shivam Upadhyay Department of Computer Science & Engineering, Krishna School of Technology, Drs. Kiran & Pallavi Patel Global University, Vadodara, Gujarat, India Author

DOI:

https://doi.org/10.32628/CSEIT2410612403

Keywords:

Click Fraud Detection, Machine Learning, Artificial Intelligence, Deep Learning

Abstract

Digital advertising is plagued by ad click fraud, which can result in large financial losses and skewed statistics. Current research on ad click fraud detection is summarized in this systematic review, which also assesses different methods and approaches. The review addresses difficulties, outlines the efficacy of various approaches, and makes recommendations for future lines of inquiry. Ad click fraud is the practice of creating phony clicks on internet ads, which can be done by malevolent humans, click farms, or automated bots. Click metrics are inflated by this fake activity, resulting in false performance statistics and squandered advertising budgets. Ad click fraud must be identified and stopped in order to preserve the efficacy and integrity of digital advertising campaigns. The objectives of this review are to list popular methods for detecting ad click fraud, assess how well they work in practical situations, talk about the drawbacks and restrictions of the approaches currently in use, and recommend future lines of inquiry to improve ad click fraud detection. The analysis concluded that when it comes to identifying ad click fraud, machine learning and artificial intelligence (AI) algorithms typically perform better than rule-based approaches. However, the caliber and variety of the training data determine how effective these methods are. The results emphasize how crucial it is to fight ad click fraud by utilizing sophisticated detection methods. To increase detection accuracy and lower financial losses, advertisers should spend money on AI and machine learning-based solutions. To keep up with changing fraud strategies, future research should concentrate on hybrid techniques, real-time detection, and cross-platform analysis.

Downloads

Download data is not yet available.

References

Malak Aljabri, Rami Mustafa A. Mohammad, 2023, “Click fraud detection for online advertising using machine learning,” Egyptian Informatics Journal, ISSN. 1110-8665, DOI. 10.1016/j.eij.2023.05.006. DOI: https://doi.org/10.1016/j.eij.2023.05.006

Mahantesh Borgi, Viraj Malik, Breznew Colaco, Pratik Dessai, Harsha Chari, Shailendra Aswale, 2021, “Advertisement Click Fraud Detection System : A Survey,” International Journal of Engineering Research & Technology (IJERT), ISSN: 2278-0181

Neeraja, Anupam, Sriram, Subhani Shaik, V. Kakulapati, 2023, “Fraud Detection of AD Clicks Using Machine Learning Techniques,” Journal of Scientific Research and Reports Volume, ISSN: 2320-0227, DOI:10.9734/JSRR/2023/v29i71762 DOI: https://doi.org/10.9734/jsrr/2023/v29i71762

Paulo S. Almeida, João J. C. Gondim, 2018 “Click Fraud Detection and Prevention System for Ad Networks,” ENIGMA - JOURNAL OF INFORMATION SECURITY AND CRYPTOGRAPHY DOI: https://doi.org/10.17648/jisc.v5i1.71

Anshuman Dash, Satyajit Pal, 2020, “Auto-Detection of Click-Frauds using Machine Learning,” IJESC - Vol. 10.

Lokesh Singh, Deepti Sisodia, N. L. Taranath, 2023, “Gradient Boosting-Based Predictive Click Fraud Detection Using Manifold Criterion Variable Elimination Gradient Boosting-Based Predictive Click Fraud Detection Using Manifold Criterion Variable,” IFIP International Federation for Information Processing 2023 Published by Springer Nature, ISBN: 9783031382963, DOI: 10.1007/978-3-031-38296-3 DOI: https://doi.org/10.1007/978-3-031-38296-3_22

Thejas G S, Kianoosh Boroojeni, Isha Bhatia, Sunitha N R, 2019, “Deep Learning-based Model to Fight Against Ad Click Fraud Deep Learning-based Model to Fight Against Ad Click Fraud”, ACM Southeast Conference—ACMSE 2019—Session 2: Short Papers—ISBN: 978-1-4503-6251-1, DOI: 10.1145/3299815.3314453 DOI: https://doi.org/10.1145/3299815.3314453

Weibin Li, Qiwei Zhong, 2021 “Multimodal and Contrastive Learning for Click Fraud Detection” License Attribution 4.0 International.

B. Viruthika, Suman Sangeeta Das, E.Manish Kumar, D Prabhu, 2020 “Detection of Advertisement Click Fraud Using Machine Learning” International Journal of Advanced Science and Technology Vol. 29, No. 5, (2020), pp. 3238 - 3245.

Thejas G.S., Surya Dheeshjith, S.S. Iyengar, N.R. Sunitha, Prajwal Badrinath, 2021 “A hybrid and effective learning approach for Click Fraud detection” Machine Learning with Applications 3 (2021) 100016. DOI: https://doi.org/10.1016/j.mlwa.2020.100016

Tanvir Rahman Akash, Md Shakil Islam, and Md Sultanul Arefin Sourav, 2024 “Enhancing business security through fraud detection in financial transactions” Global Journal of Engineering and Technology Advances, 2024, 21(02), 079–087. DOI: https://doi.org/10.30574/gjeta.2024.21.2.0205

Ananya Smirti, 2021, “Detecting of Fraud Click on Advertisement” INTERNATIONAL JOURNAL OF RESEARCH IN SCIENCE & TECHNOLOGY e-ISSN:2249-0604; p-ISSN: 2454-180X. DOI: https://doi.org/10.37648/ijrst.v11i03.004

Ranjeet Vishwakarma, Rajesh Dhakad, 2024 “Online Advertising and Fraud Click in Online Advertisement: A Survey” International Journal of Computer Applications (0975 - 8887). DOI: https://doi.org/10.5120/ijca2024923300

Elena-Adriana MINASTIREANU and Gabriela MESNITA, 2019 “Light GBM Machine Learning Algorithm to Online Click Fraud Detection” Journal of Information Assurance & Cybersecurity DOI: 10.5171/2019.263928. DOI: https://doi.org/10.5171/2019.263928

Mahesh Bathula, Rama Chaithanya Tanguturi, Srinivasa Rao Madala, 2021 “Click Fraud Detection Approaches to Analyze the Ad Clicks Performed by Malicious Code” IOP Publishing doi:10.1088/1742-6596/2089/1/012077 DOI: https://doi.org/10.1088/1742-6596/2089/1/012077