Алгоритмы интеллектуального анализа данных банковских транзакций в составе системы противодействия финансовому мошенничеству

А. Н. Никонов, А. М. Вульфин, М. М. Гаянова, М. Ю. Сапожникова

Аннотация


Статья посвящена вопросам повышения эффективности систем мониторинга транзакций (СМТ). Рассмотрены основные виды СМТ с указанием их достоинств и недостатков, также были рассмотрены различные алгоритмы интеллектуального анализа данных, применяемых в этой сфере. На основании проведенного анализа существующих систем и алгоритмов, были выбраны три классификатора: многослойный персептрон (МСП), классификатор на основе случайного леса и метод опорных векторов. Выбранные классификаторы были протестированы на натурных данных. Наилучшие показатели были отмечены для классификатора на основе случайного леса. Перспективными являются СМТ, использующие при анализе модель поведения пользователя, таким образом, следующим шагом должен стать сбор статистических данных о поведении и построение модели пользователя.


Ключевые слова


интеллектуальный анализ данных; многослойный персептрон; случайный лес; метод опорных векторов

Полный текст:

PDF

Литература


Евдокимов К. Н. Структура и состояние компьютерной преступности Российской Федерации // Юридическая наука и правоохранительная практика. 2016. Т 1. № 35. C. 86–94. [K. N. Evdokimov “Structure and state of computer crime in the Russian Federation”, (in Russian), in Yuridicheskaya nauka i pravookhranitel'naya praktika, vol. 1, no. 35, pp. 86-94, 2016.

Бизнес энциклопедия: платежные карты /И. М. Голдовский и др. Москва: ЦИПСиР, 2014. 560 с. [I. M. Goldovskiy et al. “Business encyclopedia: payment cards”, Moscow (in Russian) / TsIPSiR, 2014, P. 560.]

Huang R., Tawfik H., Nagar A. K. A novel Hybrid Artificial Immune Inspired Approach for Online Break-in Fraud Detection // Procedia Computer Science. 2012. Vol. 1. pp. 2733–2742. [R. Huang, H. Tawfik, A. K. Nagar “A novel Hybrid Artificial Immune Inspired Approach for Online Break-in Fraud Detection”, in Procedia Computer Science, vol. 1, pp. 2733-2742, 2012.]

Schaidnagel M., Petrov I., Laux F. DNA: An Online Algorithm for Credit Card Fraud Detection for Games Merchants // Data analytics 2013: The Second International Conference on Data Analytics, 2013. pp. 1–6. [M. Schaidnagel, I. Petrov, F. Laux “DNA: An Online Algorithm for Credit Card Fraud Detection for Games Merchants”, 2013, pp. 1-6.]

Patil S., Somavanshi H., Gaikward J. Credit Card Fraud Detection Using Decision Tree Induction Algorithm // International Journal of Computer Science and Mobile Computing. 2015. Vol.4. pp. 92–95. [S. Patil, H. Somavanshi, J. Gaikward “Credit Card Fraud Detection Using Decision Tree Induction Algorithm”, in International Journal of Computer Science and Mobile Computing, vol. 4, pp. 92-55, 2015.]

Delamaire L., Abdou H., Pointon J. Credit card fraud and detection techniques: a review // Bank and Bank Systems. 2009. Vol. 4. pp. 56–68. [L. Delamaire, H. Abdou, J. Pointon “Credit card fraud and detection techniques: a review”, in Bank and Bank Systems, vol. 4, pp. 56-68, 2009.]

Detecting Credit Card Fraud using Periodic Features / A. C. Bahnsen, et al // Computer Science. 2015. №. 3. pp. 37–43. [A. C. Bahnsen, et al., “Detecting Credit Card Fraud using Periodic Features”, in Computer Science, no. 3, pp. 37-43, 2015.]

A Novel Approach for Automated Credit Card Transaction Fraud Detection using Network-Based Extensions / V.V. Vlasselaer et al // Decision Support Systems. 2015. p. 38–48. [V. V. Vlasselaer, C. Bravo, O. Caelen, L. Akoglu “A Novel Approach for Automated Credit Card Transaction Fraud Detection using Network-Based Extensions”, in Decision Support Systems, p. 38-48, 2015.]

Турков П. А., Красоткина О. В., Моттль В. В. Отбор признаков в задаче классификации при смещении решающего правила // Известия Тульского государственного университета: Естественные науки. 2015. № 4. С. 67–78. [A. Turkov, O. V. Krasotkina, V. V. Mottl' “Selection of signs in the classification problem when the decision rule is shifted ”, (in Russian), in Izvestiya Tul'skogo gosudarstvennogo universiteta: Estestvennye nauki, no. 4, pp. 67-68, 2015.]

Patidar R., Sharma L. Credit Card Fraud Detection Using Neural Network // International Journal of Soft Computing and Engineering. 2011. Vol.1. pp. 32–38. [R. Patidar, L. Sharma “Credit Card Fraud Detection Using Neural Network”, in International Journal of Soft Computing and Engineering, vol. 1, pp. 32-38, 2011.]

West J., Bhattacharya M. Some Experimental Issues in Financial Fraud Mining // Procedia Computer Science. 2016. Vol. 80. pp. 1734–1744. [J. West, M. Bhattacharya “Some Experimental Issues in Financial Fraud Mining”, in Procedia Computer Science, vol. 80, pp. 1734-1744, 2016.]

Patel S., Gond S. Supervised Machine (SVM) Learning for Credit Card Fraud Detection // International Journal of Engineering Trends and Technology. 2014. Vol. 8. pp. 137–139. [S. Patel, S. Gond “Supervised Machine (SVM) Learning for Credit Card Fraud Detection”, in International Journal of Engineering Trends and Technology, vol. 8, pp. 137-139, 2014.]

Bhusari V., Patil S. International Journal of Engineering Trends and Technology // International Journal of Distributed and Parallel Systems. 2011. Vol 2. No.6. pp. 203–211. [V. Bhusari, S. Patil “International Journal of Engineering Trends and Technology”, in International Journal of Distributed and Parallel Systems, vol. 2 no. 6, pp. 203-211, 2011.]

Prakash A. Chandrasekar C. An Optimized Multiple Semi-Hidden Markov Model for Credit Card Fraud Detection // Indian Journal of Science and Technology. 2015. Vol. 8. No. 2. pp. 164–171. [A. Prakash, C. Chandrasekar “An Optimized Multiple Semi-Hidden Markov Model for Credit Card Fraud Detection”, in Indian Journal of Science and Technology, vol. 8, no. 2, pp. 163-171, 2015.]

Matheswaran P., Siva E., Rajesh R. Fraud Detection in Credit Card Using Data Mining Techniques // International Journal of Distributed and Parallel Systems. 2015. Vol. 2. Р. 11–18. [P. Matheswarn, E. Siva, R. Rajesh “Fraud Detection in Credit Card Using Data Mining Techniques”, in International Journal of Distributed and Parallel Systems, vol. 2, pp. 11-18, 2015.]

Patil S., Somavanshi H., Gaikward J., Deshmane A. Credit Card Fraud Detection Using Decision Tree Induction Algorithm // International Journal of Computer Science and Mobile Computing. 2015. Vol. 4. pp. 92–95. [S. Patil, H. Somavanshi, J. Gaikward, A. Deshmane “Credit Card Fraud Detection Using Decision Tree Induction Algorithm”, in International Journal of Computer Science and Mobile Computing, vol. 4, pp. 92-95, 2015.]

Чистяков С. П. Случайные леса: обзор // Труды Карельского научного центра РАН. 2013. № 1. С. 117–136. [S. P. Chistyakov “Random forests: a review”, (in Russian), in Trudy Karel'skogo nauchnogo tsentra RAN, no. 1, pp. 117-136, 2013.]

Salvatore J., Fan W., Lee W. Cost-based Modeling for Fraud and Intrusion Detection: Results from the JAM Project // International Journal of Computer Science and Mobile Computing. 2015. Vol. 1. Pp. 1-15. [J. Salvatore, W. Fan, W. Lee “Cost-based Modeling for Fraud and Intrusion Detection: Results from the JAM Project”, in International Journal of Computer Science and Mobile Computing, vol. 1. pp. 1-15, 2015.]

McDonald C. Real time credit card fraud detection with Apache Spark and event streaming. [Электронный ресурс] URL: https: // mapr.com/blog/real-time-credit-card-fraud-detection-apache-spark-and-event-streaming / (дата обращения 14.12.2018). [C. McDonald (2018, Dec. 14) Real time credit card fraud detection with Apache Spark and event streaming [Online]. Available: https: // mapr.com/blog/real-time-credit-card-fraud-detection-apache-spark-and-event-streaming/]

Ghosh P. Real time fraud detection with sequence mining [Электронный ресурс] URL: https://pkghosh.wordpress.com/2013/10/21/real-time-fraud-detection-with-sequence-mining/ (дата обращения 14.12.2018). [P. Ghosh (2018, Dec. 14) Real time fraud detection with sequence mining [Online]. Available: https://pkghosh.wordpress.com/2013/10/21/real-time-fraud-detection-with-sequence-mining/]

Seeja K. R. FraudMiner: A Novel Credit Card Fraud Detection Model Based on Frequent Itemset Mining. // The Scientific World Journal. 2014. Vol. 1. pp. 1–10. [K. R. Seeja “FraudMiner: A Novel Credit Card Fraud Detection Model Based on Frequent Itemset Mining”, in The Scientific World Journal, vol. 1, pp. 1-10, 2014.]

Fahmi M., Hamdy A., Nagati K. Data Mining Techniques for Credit Card Fraud Detection: Empirical Study. // Sustainable Vital Technologies in Engineering & Informatics. 2016. pp.1–9. [M. Fahmi, A. Hamdy, K. Nagati “Data Mining Techniques for Credit Card Fraud Detection: Empirical Study”, in Sustainable Vital Technologies in Engineering & Informatics, pp. 1-9, 2016.]

Watkins C. J. C. Combining cross-validation and search. // Progress in Machine Learning-Proceedings of EWSL: 10nd European Working Session on Learning. 2009. pp. 79–90. [C. J. S. Watkins “Combining cross-validation and search”, in Progress in Machine Learning-Proceedings of EWSL: 10nd European Working Session on Learning, pp. 79-90, 2009.]


Ссылки

  • На текущий момент ссылки отсутствуют.


(c) 2019 А. Н. Никонов, А. М. Вульфин, М. М. Гаянова, М. Ю. Сапожникова