A Comparative Study of Machine Learning Techniques for Credit Card Fraud Detection Based on Time Variance

Dong-Lin Li, Shantanu Rajora, Chandan Jha, Neha Bharill, Om Prakash Patel, Sudhanshu Joshi, Deepak Puthal, Mukesh Prasad

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a comparative performance of ten different machine learning algorithms, done on a credit card fraud detection application. The machine learning methods have been classified into two groups namely classification algorithms and ensemble learning group. Each group is comprised of five different algorithms. Besides, the 'Time' feature is introduced in the data set and performances of the algorithms are studied with and without the 'Time' feature. Two algorithms of the ensemble learning group have been found to perform better when the used dataset does not include the 'Time' feature. However, for the classification algorithms group, three classifiers are found to show better predictive accuracies when all attributes are included in the used dataset. The rest of the machine learning models have approximate similar scores between these datasets.
Original languageEnglish
Title of host publication2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI)
PublisherIEEE
Pages1958-1963
Number of pages6
ISBN (Print)978-1-5386-9276-9
StatePublished - Nov 2018

Keywords

  • fraud detection
  • ensemble-learning
  • non-ensemble learning
  • unbalanced data
  • REGRESSION

Fingerprint Dive into the research topics of 'A Comparative Study of Machine Learning Techniques for Credit Card Fraud Detection Based on Time Variance'. Together they form a unique fingerprint.

Cite this