Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)

<Previous Article In Volume
Next Article In Volume>

Two-Tiered Sampling Methodology for Enhancing Detection of Malicious Ad Click Behavior

Authors
Lokesh Singh1, Deepti Sisodia1, *
1Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal, India
*Corresponding author. Email: deepti.sisodia@manipal.edu
Corresponding Author
Deepti Sisodia
Available Online 31 December 2025.
DOI
10.2991/978-94-6463-978-0_47How to use a DOI?
Keywords
two-tiered sampling; malicious behaviour; pay_per_click; click fraud; class imbalance; data_level sampling techniques
Abstract

Detecting fraudulent clicks in digital advertising remains a complex issue due to the disproportionate distribution of class labels within user-click datasets. The quantity of legitimate publishers usually surpasses that of fraudulent, resulting in classification models exhibiting bias towards the predominant class. This paper presents a two-phase data sample strategy to address the imbalance, employing oversampling, undersampling, and hybrid strategies successively. The first stage involves a crude adjustment to lessen class dominance, while the second stage refines the data structure with the goal of maintaining minority class features. The dual-stage sampling method aims to enhance the model’s capacity to differentiate between authentic and fraudulent behaviours by rebalancing the data in a more systematic way. Experimental assessment reveals significant enhancements in classification efficacy, especially in precision and the identification of infrequent fraudulent cases.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
Series
Advances in Engineering Research
Publication Date
31 December 2025
ISBN
978-94-6463-978-0
ISSN
2352-5401
DOI
10.2991/978-94-6463-978-0_47How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Lokesh Singh
AU  - Deepti Sisodia
PY  - 2025
DA  - 2025/12/31
TI  - Two-Tiered Sampling Methodology for Enhancing Detection of Malicious Ad Click Behavior
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 548
EP  - 559
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_47
DO  - 10.2991/978-94-6463-978-0_47
ID  - Singh2025
ER  -