Credit card fraud detection is an important application of outlier detection. Due to drastic increase in digital frauds, there is a loss of billions dollars and therefore various techniques are evolved for fraud detection and applied to diverse business fields. The traditional fraud detection schemes use data analysis methods that require knowledge about different domains such as financial, economics, law and business practices. The current fraud detection techniques may be offline or online, and may use neural networks, clustering, genetic algorithm, decision tree etc. There are various outlier detection techniques are available such as statistical based, density based, clustering based and so on. This paper projected to find credit card fraud by using appropriate outlier detection technique, which is suitable for online applications where large scale data is involved. The method should also work efficiently for applications where memory and computation limitations are present. Here we have discussed one such unsupervised method Principal Component Analysis(PCA) to detect an outlier.
[1]
Hans-Peter Kriegel,et al.
LOF: identifying density-based local outliers
,
2000,
SIGMOD '00.
[2]
Heng Tao Shen,et al.
Principal Component Analysis
,
2009,
Encyclopedia of Biometrics.
[3]
Lindsay I. Smith,et al.
A tutorial on Principal Components Analysis
,
2002
.
[4]
Philip S. Yu,et al.
Outlier detection for high dimensional data
,
2001,
SIGMOD '01.
[5]
VARUN CHANDOLA,et al.
Anomaly detection: A survey
,
2009,
CSUR.
[6]
Charu C. Aggarwal,et al.
Outlier Analysis
,
2013,
Springer New York.
[7]
R. Nagaraj,et al.
Anomaly Detection via Online Oversampling Principal Component Analysis
,
2014
.
[8]
Xiangliang Zhang,et al.
A Novel Intrusion Detection Method Based on Principle Component Analysis in Computer Security
,
2004,
ISNN.
[9]
Chang-Tien Lu,et al.
Survey of fraud detection techniques
,
2004,
IEEE International Conference on Networking, Sensing and Control, 2004.