تشخیص تراکنش‌های مشکوک در کارت‌های اعتباری با استفاده از الگوریتم Extra Trees Classifier
تشخیص تراکنش‌های مشکوک در کارت‌های اعتباری با استفاده از الگوریتم Extra Trees Classifier
محورهای موضوعی : دانش مالی تحلیل اوراق بهادار
عرفان عابدینی 1 , محمود همت فر 2
1 - داﻧﺸﺠﻮی کارشناسی ارشد، گروه ﻣﺪﯾﺮﯾﺖ مالی، داﻧﺸﮑﺪه ﻣﺪﯾﺮﯾﺖ و اﻗﺘﺼﺎد، واﺣﺪ ﻋﻠﻮم و ﺗﺤﻘﯿﻘﺎت، داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ، تهران، ایران
2 - دانشیار، گروه حسابداری، واحد بروجرد، داﻧﺸﮕﺎه آزاد اﺳﻼﻣﯽ، بروجرد، ایران (ﻧﻮﯾﺴﻨﺪه ﻣﺴﺌﻮل)
کلید واژه: یادگیری ماشین, یادگیری ماشین در تشخیص تقلب, تقلب کارت اعتباری, تقلب آنلاین, کلاهبرداری کارت اعتباری.,
چکیده مقاله :
در سال‌های گذشته، با توسعه تجارت الکترونیک، کارت‌های اعتباری به طور گسترده تری در تراکنش‌ها به دلایل مختلف از جمله سهولت کارایی مورد استفاده قرار گرفته اند. تقلب و تراکنش های غیرمجاز کارت های اعتباری به دلیل افزایش استفاده از آنها در حال تبدیل شدن به مسئله‌ای رایج و مهم است. بنابراین، مسئولیت بزرگی بر عهده مؤسسات مالی است که مکانیزم موجود خود را به‌روز کنند تا از این اقدامات غیرمجاز جلوگیری کنند. عدم وجود یک الگوی مشخص و همچنین عدم توازن در تعداد تراکنش های مجاز و غیرمجاز، توسعه مدل و ساخت سیستم های تشخیص تقلب را با مشکل مواجه کرده است. هدف اصلی این مطالعه، ایجاد یک راهکار مناسب، دقیق و سریع برای تشخیص تقلب در کارت های اعتباری مبتنی بر یادگیری ماشین است. مدل پیشنهادی در این مقاله، شامل استفاده از روش SMOTE برای مدیریت داده‌های نامتوزان و الگوریتم Extra Trees Classifier برای شناسایی تراکنش غیرمجاز است. همچنین معیارهای مختلف بررسی دقت و کارایی نشان از عملکرد موثر مدل پیشنهادی میباشد.
In recent years, with the development of e-commerce, credit cards have been widely used in transactions for various reasons, including the ease and efficiency they provide. Fraud and unauthorized transactions with credit cards have become a common and significant problem due to the increased use of credit cards. Therefore, financial institutions bear a significant responsibility to update their existing mechanisms to prevent such unauthorized actions. The lack of a specific pattern and an imbalance in the number of authorized and unauthorized transactions have posed challenges in developing fraud detection models and systems. The main objective of this study is to create a suitable, accurate, and fast solution for fraud detection in credit cards based on machine learning. The proposed model in this article includes the use of the SMOTE method to handle imbalanced data and the Extra Trees Classifier algorithm to identify unauthorized transactions. Various metrics examining accuracy and performance indicate the effective performance of the proposed model.
S. Kotsiantis, D. Kanellopoulos, and P. Pintelas,” Handling imbalanced datasets: A review,” GESTS international transactions on computer science and engineering 30, no. 1, 2006, pp. 25-36.
Bhutani KBH (2021) COVID-19-the inflexion point for E-commerce. Indian J Econ Bus 20(2),PP 649-659.
Abdelrhim M, Elsayed A (2020) The effect of COVID-19 spread on the E-commerce market: the case of the 5 Largest E-Commerce Companies in the World. In: Social Science Research Network, Rochester, NY, SSRN Scholarly Paper ID 3621166, Jun. 2020. 10.2139/ssrn.3621166.
UNCTAD (2020) COVID-19 and e-commerce: Findings from a survey of online consumers in 9 countries. [Online accessed 6-March-2022].https://unctad.org/system/files/officialdocument/dtlstictinf2020d1_en.pdf
Guthrie C, Fosso-Wamba S, Arnaud JB. Online consumer resilience during a pandemic: an exploratory study of e-commerce behavior before, during and after a COVID-19 lockdown. J Retail Consum Serv. 2021;61:102570. doi: 10.1016/j.jretconser.2021.102570.
C. Meng, L. Zhou, and B. Liu, ” A case study in credit fraud detection with SMOTE and XGBoost,” In Journal of Physics: Conference Series, vol. 1601, no. 5, p. 052016. IOP Publishing, 2020.
W. Kramer,” Wojtek J. Krzanowski and David J. Hand: ROC curves for ¨ continuous data,” 2011, p. 979.
G. Menardi, and N. Torelli,” Training and assessing classification rules with imbalanced data,” Data mining and knowledge discovery 28, no. 1, 2014, pp. 92-122.
I. Vejalla, S. P. Battula, K. Kalluri and H. K. Kalluri, "Credit Card Fraud Detection Using Machine Learning Techniques," 2023 2nd International Conference on Paradigm Shifts in Communications Embedded Systems, Machine Learning and Signal Processing (PCEMS), Nagpur, India, 2023, pp. 1-4, doi: 10.1109/PCEMS58491.2023.10136040.
Maniraj S P, Saini A, Ahmed S, et al. Credit card fraud detection using machine learning and data science[J]. International Journal of Engineering Research, 2019, 8(9): 110-115.
Santoso SHH, Wibowo W. Integration of synthetic minority oversampling technique for imbalanced class. Indones J Electr Eng Comput Sci. 2019;13(1):102–108. doi: 10.11591/ijeecs.v13.i1.pp102-108.
Mishra A, Ghorpade C (2018) Credit card fraud detection on the skewed data using various classification and ensemble techniques. In: 2018 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), 2018, pp 1–5. 10.1109/SCEECS.2018.8546939
Pozzolo AD, Caelen O, Johnson RA, Bontempi G (2015) Calibrating probability with undersampling for unbalanced classification. In: 2015 IEEE Symposium series on computational intelligence, 2015, pp 159–166. 10.1109/SSCI.2015.33
Prasetiyo B, Alamsyah A, Muslim MA, Baroroh N. Evaluation performance recall and F2 score of credit card fraud detection unbalanced dataset using SMOTE oversampling technique. J Phys Conf Ser. 2021;1918(4):042002. doi: 10.1088/1742-6596/1918/4/042002.
Krishna, M.Vamsi and J. Praveenchandar. “Comparative Analysis of Credit Card Fraud Detection using Logistic regression with Random Forest towards an Increase in Accuracy of Prediction.” 2022 International Conference on Edge Computing and Applications (ICECAA) (2022): 1097-1101.
S. Khatri, A. Arora and A. P. Agrawal, "Supervised machine learning algorithms for credit card fraud detection: A comparison", Proc. 10th Int. Conf. Cloud Comput. Data Sci. Eng. (Confluence), pp. 680-683, Jan. 2020.
N. K. Trivedi, S. Simaiya, U. K. Lilhore and S. K. Sharma, "An efficient credit card fraud detection model based on machine learning methods", Int. J. Adv. Sci. Technol., vol. 29, no. 5, pp. 3414-3424, 2020
S. Rajora, D. L. Li, C. Jha, N. Bharill, O. P. Patel, S. Joshi, et al., "A comparative study of machine learning techniques for credit card fraud detection based on time variance", Proc. IEEE Symp. Comput. Intell. (SSCI), pp. 1958-1963, Nov. 2018.
Dornadula V N, Geetha S. Credit card fraud detection using machine learning algorithms[J]. Procedia computer science, 2019, 165: 631-641.
Sara makki, Zainabassaghir, Yehiataher, Rafiqul haque, Mohand said, Hacid, Hassan zeneddine," An Experimental Study with Imbalanced classification approaches for Credit card Fraud Detection", IEEE, 2019
E. A. Amusan, O. M. Alade, J. O. Emuoyibofarhe, and O. D. Fenwa, “Credit Card Fraud Detection on Skewed Data using Machine Learning Techniques,” LAUJCI, 2021. [Online]. Available: www.laujci.lautech.edu.ng
E. A. M.Suresh Kumar, V.Soundarya , S.Kavitha , E.S.Keerthika, CREDIT CARD FRAUD DETECTION USING RANDOM FOREST ALGORITHM. 2019. Alharbi, Abdullah et al. “A Novel text2IMG Mechanism of Credit Card Fraud Detection: A Deep Learning Approach.” Electronics (2022)
“Credit Card Fraud Detection.” Kaggle, 23 Mar. 2018, www.kaggle.com/datasets/mlg-ulb/creditcardfraud.
Liu, Xuebo et al. “An Imbalanced Signal Modulation Classification And Evaluation Method Based On Synthetic Minority Over-Sampling Technique.” IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium (2023): 6224-6227.
Akhtar, Muhammad Shoaib, and Tao Feng. “Evaluation of Machine Learning Algorithms for Malware Detection.” Sensors (Basel, Switzerland) vol. 23,2 946. 13 Jan. 2023, doi:10.3390/s23020946
Martiello Mastelini, Saulo et al. “Online Extra Trees Regressor.” IEEE transactions on neural networks and learning systems vol. 34,10 (2023): 6755-6767. doi:10.1109/TNNLS.2022.3212859
Dhananjay, B. et al. “Cardiac signals classification based on Extra Trees model.” 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN) (2021): 402-406.
Padmaja, Budi et al. “A Novel Random Split Point Procedure Using Extremely Randomized (Extra) Trees Ensemble Method for Human Activity Recognition.” EAI Endorsed Trans. Pervasive Health Technol. 6 (2020): e5.
Zafari, Azar et al. “Land Cover Classification Using Extremely Randomized Trees: A Kernel Perspective.” IEEE Geoscience and Remote Sensing Letters 17 (2020): 1702-1706.
Bombara, Giuseppe and Calin A. Belta. “Offline and Online Learning of Signal Temporal Logic Formulae Using Decision Trees.” ACM Transactions on Cyber-Physical Systems 5 (2021): 1 - 23.
