2026-05-04T18:35:07.250Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:11832 2026-02-03T17:11:59Z 3

Click Pattern Classification Using Modified Metaheuristic Optimized Long-Short Term Neural Networks for Fraud Detection, Chapter in LNNS Lecture Notes in Networks and Systems: ICIVC 2025: Intelligent Vision and Computing, Springer, volume 1710 2026 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/11832 https://link.springer.com/chapter/10.1007/978-3-032-10664-3_1 L. Babic S. Ivanovic L. Jovanovic M. Markovic Blagojevic V. Zeljkovic M. Zivkovic B. Radomirovic N. Bacanin Fraudulent activities, particularly click fraud, present a significant challenge in online advertising, negatively impacting advertisers as well as adverting platforms. As attackers continuously evolve their strategies to bypass existing detection mechanisms, there is a pressing need for adaptive techniques capable of identifying patterns and determining appropriate actions. This research examines the use of artificial intelligence (AI) classifier-based detection, particularly leveraging long short term memory (LSTM) models optimized by modified metaheuristic algorithms. A modified variant of the recently developed elk herd optimization (EHO) algorithm, which incorporates an adaptive hill climbing strategy, is introduced to address the constraints of the baseline method and applied for hyperparameter tuning of LSTM training and architecture parameters. The proposed approach is evaluated and a comparative analysis carried out in a set of simulations to determine suitable LSTM parameters that demonstrated favorable outcomes for click fraud detection. Simulations on a real-world dataset demonstrate promising results, with the highest-performing model obtaining an accuracy of 0.792701. bookPart Springer, Cham 1 14 10.1007/978-3-032-10664-3_1 LNNS Lecture Notes in Networks and Systems: ICIVC 2025: Proceedings of International Conference on Intelligent Vision and Computing, volume 1710