TY - GEN
T1 - An Efficient Method for Detecting Fraudulent Transactions Using Classification Algorithms on an Anonymized Credit Card Data Set
AU - Manlangit, Sylvester
AU - Azam, Sami
AU - Shanmugam, Bharanidharan
AU - Kannoorpatti, Krishnan
AU - Jonkman, Mirjam
AU - Balasubramaniam, Arasu
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.
AB - Credit card fraudulent transactions are causing businesses and banks to lose time and money. Detecting fraudulent transactions before a transaction is finalized will help businesses and banks to save resources. This research aims to compare the fraud detection accuracy of different sampling techniques and classification algorithms. An efficient method of detecting fraud using machine learning is proposed. Anonymized data set from Kaggle was used for detecting fraudulent transactions. Each transaction has been labeled as either a fraudulent transaction or not. The severe imbalance between fraud and non-fraudulent data caused the algorithms to under-perform. This was addressed with the application of sampling techniques. The combination of undersampling and SMOTE raised the recall accuracy of the classification algorithm. k-NN algorithm showed the highest recall accuracy compared to the other algorithms.
KW - Anonymized data
KW - Credit card
KW - Fraud detection
UR - http://www.scopus.com/inward/record.url?scp=85044475668&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-76348-4_41
DO - 10.1007/978-3-319-76348-4_41
M3 - Conference Paper published in Proceedings
AN - SCOPUS:85044475668
SN - 9783319763477
T3 - Advances in Intelligent Systems and Computing
SP - 418
EP - 429
BT - Intelligent Systems Design and Applications - 17th International Conference on Intelligent Systems Design and Applications ISDA 2017
A2 - Abraham, Ajith
A2 - Muhuri, Pranab
A2 - Muda, Azah
A2 - Gandhi, Niketa
PB - Springer-Verlag London Ltd.
CY - Cham, Switzerland
T2 - 17th International Conference on Intelligent Systems Design and Applications, ISDA 2017
Y2 - 14 December 2017 through 16 December 2017
ER -