TY - GEN
T1 - Credit Card Fraud Detection Using Random Forest and K-Nearest Neighbors (KNN) Algorithms
AU - Alhabib, Abdulaziz Abdulrhman
AU - Alasiri, Abdulaziz Fae
AU - Alharbi, Mazen Bunayan
AU - Ahmad, Sultan
AU - Eljialy, A. E.M.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In this paper, we explored the application of both the Random Forest and K-Nearest Neighbors (KNN) algorithms for fraud detection. Fraudulent activities pose significant threats to various industries, making their detection crucial. We reviewed related works on fraud detection, highlighting the effectiveness of both the Random Forest and KNN methods. We proposed a system utilizing a combination of Random Forest and KNN models for credit card fraud detection, detailing its architecture and methodology. The system preprocesses and splits data, trains the models, and evaluates their performance on a testing set. We analyzed the results, demonstrating the accuracy, robustness, and scalability of the proposed system. Additionally, we presented data on the most common hours for fraudulent transactions and the top jobs associated with them. Overall, this study emphasizes the efficacy of utilizing both Random Forest and KNN algorithms in mitigating the risks associated with fraud and offers a valuable tool for safeguarding against financial malfeasance.
AB - In this paper, we explored the application of both the Random Forest and K-Nearest Neighbors (KNN) algorithms for fraud detection. Fraudulent activities pose significant threats to various industries, making their detection crucial. We reviewed related works on fraud detection, highlighting the effectiveness of both the Random Forest and KNN methods. We proposed a system utilizing a combination of Random Forest and KNN models for credit card fraud detection, detailing its architecture and methodology. The system preprocesses and splits data, trains the models, and evaluates their performance on a testing set. We analyzed the results, demonstrating the accuracy, robustness, and scalability of the proposed system. Additionally, we presented data on the most common hours for fraudulent transactions and the top jobs associated with them. Overall, this study emphasizes the efficacy of utilizing both Random Forest and KNN algorithms in mitigating the risks associated with fraud and offers a valuable tool for safeguarding against financial malfeasance.
KW - Credit card
KW - Fraud detection
KW - KNN
KW - Random Forest
KW - Transactions
UR - http://www.scopus.com/inward/record.url?scp=85213014905&partnerID=8YFLogxK
U2 - 10.1007/978-981-97-7371-8_30
DO - 10.1007/978-981-97-7371-8_30
M3 - Conference contribution
AN - SCOPUS:85213014905
SN - 9789819773701
T3 - Lecture Notes in Networks and Systems
SP - 383
EP - 395
BT - Proceedings of 5th International Conference on Computing, Communications, and Cyber-Security - IC4S 2023
A2 - Gonçalves, Paulo J. Sequeira
A2 - Singh, Pradeep Kumar
A2 - Tanwar, Sudeep
A2 - Epiphaniou, Gregory
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th International Conference on Computing, Communications, and Cyber Security, IC4S 2023
Y2 - 29 February 2024 through 1 March 2024
ER -