Today technology is increasing at very rapid pace, which can be used for good as well as for bad purposes. So with this growing technology e-commerce and online transactions also grown up which mostly contain transactions through credit cards. Credit cards help People to enjoy buy now and pay later for both online and offline purchases. It provides cashless shopping at every shop in all countries. As the usage of credit cards is increasing more, the chances of credit card frauds are also increasing dramatically. Credit card system is most vulnerable for frauds. These credit card frauds costs financial companies and consumers a very huge amount of money annually, fraudsters always try to find new methods and tricks to commit these illegal and outlaw actions. Online transaction fraud detection is most challenging issue for banks and financial companies. So it is much essential for banks and financial companies to have efficient fraud detection systems to reduce their losses due to these credit card fraud transactions. Various approaches have been found by many researchers till date to detect these frauds and to reduce them. Comparison of Local Outlier Factor and Isolation Factor algorithms using python and their detailed experimental results are proposed in this paper. After the analysis of the dataset we got the accuracy of 97% by Local Outlier Factor and 76% by Isolation Forest.

Fraud Detection, Isolation Forest, Local Outlier Factor, Credit card, Dataset

[1] Nilsonreport.com. (2019). [online] Available at: https://nilsonreport.com/upload/content_promo/The_Nilson_Report_10-17-2016.pdf [Accessed 6 May 2019].
[2].Machine Learning Group, “Credit Card Fraud Detection,” Kaggle,23-Mar-2018. [Online].Available:https://www.kaggle.com/mlgulb/creditcardfraud. [Accessed: 06-May-2019].
[3]. I. Trivedi, M. M, and M. Mridushi, “Credit Card Fraud Detection,” Ijarcce, vol. 5, no. 1, pp. 39–42, 2016.
[4]. R. Banerjee, G. Bourla, S. Chen, S. Purohit, and J. Battipaglia, “Comparative Analysis of Machine Learning Algorithms through Credit Card Fraud Detection,” pp. 1–10, 2018.
[5]. T. Patel and M. O. Kale, “A Secured Approach to Credit Card Fraud Detection Using Hidden Markov Model,” vol. 3, no. 5, pp. 1576–1583, 2014.
[6]. D. Tripathi, T. Lone, Y. Sharma, and S. Dwivedi, “Credit Card Fraud Detection using Local Outlier Factor,” Int. J. Pure Appl. Math., vol. 118, no. 7, pp. 229–234, 2018.
[7]. C. P. Lim, M. Seera, A. K. Nandi, K. Randhawa, and C. K. Loo, “Credit Card Fraud Detection Using AdaBoost and Majority Voting,” IEEE Access, vol. 6, no. 11, pp. 14277–14284, 2018.
[8]. I. Sohony, R. Pratap, and U. Nambiar, “Ensemble learning for credit card fraud detection,” vol. 13, no. 24, pp. 289–294, 2018.
[9]. D. Sánchez, M. A. Vila, L. Cerda, and J. M. Serrano, “Association rules applied to credit card fraud detection,” Expert Syst. Appl., vol. 36, no. 2 PART 2, pp. 3630–3640, 2009.
[10]. J. T. S. Quah and M. Sriganesh, “Real time credit card fraud detection using computational intelligence,” IEEE Int. Conf. Neural Networks - Conf. Proc., vol. 35, pp. 863–868, 2007.
[11]. H. A. Shukur, “Credit Card Fraud Detection Using Machine Learning methodologies,” vol. 8, no. 3, pp. 257–260, 2019.
[12] "Local outlier factor", En.wikipedia.org, 2019. [Online]. Available:https://en.wikipedia.org/wiki/Local_outlier_factor.[Accessed: 06- May- 2019].
[13]. "Isolation forests for anomaly detection improve fraud detection.", Blog Total Fraud Protection, 2019. [Online]. Available: https://blog.easysol.net/using-isolation-forests-anamoly-detection/. [Accessed: 12- Apr- 2019].