Novel machine learning approach for analyzing anonymous credit card fraud patterns

Sylvester Manlangit, Sami Azam, Bharanidharan Shanmugam, Asif Karim

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique
(SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32% and 97.44% respectively for k-NN and 100% and 98.24% respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown.
Original languageEnglish
Pages (from-to)175-202
Number of pages28
JournalInternational Journal of Electronic Commerce Studies
Volume10
Issue number2
DOIs
Publication statusPublished - 2019

Fingerprint

Learning systems
Principal component analysis
Feature extraction
Knowledge based systems

Cite this

@article{de554095969645cdb638fab8ecacbd81,
title = "Novel machine learning approach for analyzing anonymous credit card fraud patterns",
abstract = "Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique(SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32{\%} and 97.44{\%} respectively for k-NN and 100{\%} and 98.24{\%} respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown.",
keywords = "Fraudulent Credit Card Transactions, K-NN, SMOTE, PCA, Machine learning",
author = "Sylvester Manlangit and Sami Azam and Bharanidharan Shanmugam and Asif Karim",
year = "2019",
doi = "10.7903/ijecs.1732",
language = "English",
volume = "10",
pages = "175--202",
journal = "International Journal of Electronic Commerce Studies",
issn = "2073-9729",
publisher = "Academy of Taiwan Information Systems Research",
number = "2",

}

Novel machine learning approach for analyzing anonymous credit card fraud patterns. / Manlangit, Sylvester; Azam, Sami; Shanmugam, Bharanidharan; Karim, Asif.

In: International Journal of Electronic Commerce Studies, Vol. 10, No. 2, 2019, p. 175-202.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Novel machine learning approach for analyzing anonymous credit card fraud patterns

AU - Manlangit, Sylvester

AU - Azam, Sami

AU - Shanmugam, Bharanidharan

AU - Karim, Asif

PY - 2019

Y1 - 2019

N2 - Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique(SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32% and 97.44% respectively for k-NN and 100% and 98.24% respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown.

AB - Fraudulent credit card transactions are on the rise and have become a significantly problematic issue for financial intuitions and individuals. Various methods have already been implemented to handle the issue, but the embezzlers have always managed to employ innovative tactics to circumvent a number of security measures and execute the fraudulent transactions. Thus, instead of a rule-based system, an intelligent and adaptable machine learning based algorithm should be an answer to tackle such sophisticated digital theft. The presented framework uses k-NN for classification and utilises Principal Component Analysis (PCA) for raw data transformation. Neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique(SMOTE) and a distance-based feature selection method was employed. The proposed process performed well by having a precision and F-Score of 98.32% and 97.44% respectively for k-NN and 100% and 98.24% respectively for Time subset when using the misclassified instances. This work also demonstrates a larger and clearer classification breakdown, which aids in achieving higher precision rate and improved recall rate. In a view to accomplish such high accuracy, the original datum was transformed using Principal Component Analysis (PCA), neighbours (anomalies in data) were created using Synthetic Minority Oversampling Technique (SMOTE) and a distance based feature selection method was employed. The proposed process performed well when using the misclassified instances in the test dataset used in the previous work, while demonstrating a larger and clearer classification breakdown.

KW - Fraudulent Credit Card Transactions

KW - K-NN

KW - SMOTE

KW - PCA

KW - Machine learning

U2 - 10.7903/ijecs.1732

DO - 10.7903/ijecs.1732

M3 - Article

VL - 10

SP - 175

EP - 202

JO - International Journal of Electronic Commerce Studies

JF - International Journal of Electronic Commerce Studies

SN - 2073-9729

IS - 2

ER -