Explainable Credit Card Fraud Detection with Image Conversion

被引:8
作者
Terzi, Duygu Sinanc [1 ]
Demirezen, Umut [2 ]
Sagiroglu, Seref [1 ]
机构
[1] Gazi Univ, Dept Comp Engn, Fac Engn, Ankara, Turkey
[2] Presidency Republ Turkey, Artificial Intelligence & Big Data Unit, Digital Transformat Off, Ankara, Turkey
来源
ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL | 2021年 / 10卷 / 01期
关键词
Fraud detection; Time series; Deep learning; Explainable artificial intelligence; Image conversion; TIME-SERIES;
D O I
10.14201/ADCAIJ20211016376
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The increase in the volume and velocity of credit card transactions causes class imbalance and concept deviation problems in data sets where credit card fraud is detected. These problems make it very difficult for traditional approaches to produce robust detection models. In this study, a different perspective has been developed for this problem and a novel approach named Fraud Detection with Image Conversion (FDIC) is proposed. FDIC handles credit card transactions as time series and transforms them into images. These images, which comprise temporal correlations and bilateral relationships of features, are classified by a convolutional neural network architecture as fraudulent or legitimate. When the obtained results are compared with the related studies, FDIC has the best F1-score and recall values, which are 85.49% and 80.35%, respectively. This shows that FDIC is better than other studies in detecting fraudulent instances associated with high cost. Since the images created during the FDIC process are difficult to interpret, a new explainable artificial intelligence approach is also presented. In this way, feature relationships that have a dominant effect on fraud detection are revealed.
引用
收藏
页码:63 / 76
页数:14
相关论文
共 34 条
[1]  
Abakarim Y., 2018, P 12 INT C INTELLIGE, P1
[2]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[3]   A survey of machine-learning and nature-inspired based credit card fraud detection techniques [J].
Adewumi A.O. ;
Akinyelu A.A. .
International Journal of System Assurance Engineering and Management, 2017, 8 (Suppl 2) :937-953
[4]  
Al-Shabi M. A., 2019, J. Adv. Math. Comput. Sci., V33, P1
[5]  
[Anonymous], 2015, ACS SYM SER
[6]  
[Anonymous], Nilson Report 1164
[7]  
Arif M., 2015, INT J U E SERVICE SE, V8, P165, DOI [10.14257/ijunesst.2015.8.3.15, DOI 10.14257/IJUNESST.2015.8.3.15]
[8]   The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances [J].
Bagnall, Anthony ;
Lines, Jason ;
Bostrom, Aaron ;
Large, James ;
Keogh, Eamonn .
DATA MINING AND KNOWLEDGE DISCOVERY, 2017, 31 (03) :606-660
[9]   Nature-Inspired Techniques in the Context of Fraud Detection [J].
Behdad, Mohammad ;
Barone, Luigi ;
Bennamoun, Mohammed ;
French, Tim .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2012, 42 (06) :1273-1290
[10]  
Clevert Djork-Arne, 2016, FAST ACCURATE DEEP N