Credit Card Fraud Detection Using Unsupervised Machine Learning Algorithms
  IJCTT-book-cover
 		          
 
© 2021 by IJCTT Journal
Volume-69 Issue-8
Year of Publication : 2021
Authors : Hariteja Bodepudi
DOI :  10.14445/22312803/IJCTT-V69I8P101

How to Cite?

Hariteja Bodepudi, "Credit Card Fraud Detection Using Unsupervised Machine Learning Algorithms," International Journal of Computer Trends and Technology, vol. 69, no. 8, pp. 1-3, 2021. Crossref, https://doi.org/10.14445/22312803/IJCTT-V69I8P101

Abstract
In the modern era, the usage of the internet has increased a lot these days and becomes an essential part of the life. As the e-commerce has increased, the buying and selling the products over the internet becomes more easy and flexible. The usage of online shopping, online bill payment has increased a lot these days with the introduction of the modern technology like online banking, credit card payments. Due to the increase of the online payment and online shopping, the risk of credit card usage also increased as the credit card was used in many places as it becomes hard for the bank to distinguish the real transactions of the consumer versus the fraud transactions. Also, the credit card fraud transaction can also happen if the customer accidentally loses the credit card. So, it becomes complex for the banks to stop the fraud transactions at that point. This paper talks about how to detect the fraud transactions and block the payments before processing by using the Machine Learning on a real-time basis. This paper clearly explains about how the anomalies can be detected in an unsupervised approach and to achieve the higher accuracy. This Anomaly detection process used in this paper can be applied in a wide range of applications like fraud detections in banking, underbilling/overbilling for customers in telecommunications, security monitoring, network traffic, health care, and a wide range of manufacturing industries.

Keywords
Anomaly, Machine Learning, Supervised Learning, Unsupervised Learning.

Reference

[1] H. Bodepudi., Faster The Slow Running RDBMS Queries With Spark Framework, (2020). [Online]. Available: https://www.researchgate.net/publication/347390599_Faster_The_ Slow_Running_RDBMS_Queries_With_Spark_Framework. [Accessed 07 2021].
[2] H. Bodepudi., Data Transfer Between RDBMS and HDFS By Using The Spark Framework In Sqoop For Better Performance, Internation Journal of Computer Trends and Technology, 69(3) (2021) 1.
[3] Anaomaly-Detection., [Online]. Available: https://avinetworks.com/glossary/anomaly-detection/. [Accessed July 2021]., (2021).
[4] What is Machine Learning., [Online]. Available: https://www.ibm.com/cloud/learn/machine-learning. [Accessed July 2021].
[5] Popular Machine Learning Methods, [Online]. Available: https://www.sas.com/enus/insights/analytics/machinelearning.html. [Accessed July 2021].
[6] CreditCard Data, [Online].Available:https://www.kaggle.com/mlgulb/creditcardfraud?select=creditcard.csv. [Accessed July 2021].
[7] H2o.ai Data Science, ,[Online]. Available: https://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/if.html.
[8] Isolation Forest Example, [Online]. Available: https://scikitlearn.org/stable/auto_examples/ensemble/plot_isolation_forest.htm l#sphx-glr-auto-examples-ensemble-plot-isolation-forest-py.
[9] Anaomaly Detection With Local Outlier Factor, [Online]. Available: https://www.datatechnotes.com/2020/04/anomalydetection-with-local-outlier-factor-in-python.html.
[10] Outlier detection with Local Outlier Factor (LOF), [Online]. Available:https://scikitlearn.org/stable/auto_examples/neighbors/pl ot_lof_outlier_detection.html. [Accessed August 2021].
[11] One-Class Support Vector Machine., [Online]. Available: https://www.xlstat.com/en/solutions/features/1-class-supportvector-machine.
[12] One-Class SVM.M [Online]. Available: https://scikitlearn.org/stable/auto_examples/svm/plot_oneclass.html#sphx-glrauto-examples-svm-plot-oneclass-py.