2026-04-17T17:40:11.191Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:9637 2024-12-03T20:10:47Z 3

Predicting Credit Card Churn Using Support Vector Machine Tuned by Modified Reptile Search Algorithm, Chapter in AIS Algorithms for Intelligent Systems: WCAIAA 2023: World Conference on Artificial Intelligence: Advances and Applications, Springer 2023 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/9637 https://link.springer.com/chapter/10.1007/978-981-99-5881-8_6 M. Stankovic L. Jovanovic V. Marevic A. Balghouni M. Zivkovic N. Bacanin As economies continue to move forward credit card providers face novel emerging problems. A pressing economic issue that has become prominent in recent years is the phenomenon of credit card churn. A process in which malicious users sign up for new credit cards simply to profit from new user benefits, only to close the card once the perks expire. The application of novel artificial intelligence (AI) techniques is a promising approach for accurately handling the immense amounts of complex information present in the financial sector. Furthermore, the utilization of AI for this problem has not yet been sufficiently explored. This works attempts to address the prominent research gap by applying a support vector machine (SVM) to forecasting credit card churn. To attain the best possible performance a recently introduced reptile search algorithm (RSA) is tasked with selecting the best possible hyperparameters of an SVM. Furthermore, an improved version of the RSA is proposed in hopes of enhancing performance. The proposed optimized approach is applied to real-world data concerning credit card churn, and the results indicated the proposed approach outperformed all other tested algorithms applied to the same task, achieving an accuracy score of 99.56%, weighted average precision of 0.91, weighted average recall of 0.92, and weighted average f-1 score of 0.91. These empirical findings suggest the high predictive potential of the proposed method. bookPart Springer, Singapore 63 77 10.1007/978-981-99-5881-8_6 AIS Algorithms for Intelligent Systems: WCAIAA 2023: World Conference on Artificial Intelligence: Advances and Applications