ABSTRACT
Fraud has become a trillion-dollar industry today. Some finance companies have separate domain expert teams and data scientists who are working on identifying fraudulent activities. Data Scientists often use complex statistical models to identify frauds. However, there are many disadvantages to this approach. Fraud detection is not real-time and therefore, in many cases fraudulent activities are identified only after the actual fraud has happened. These methodologies are prone to human errors. In addition, it requires expensive, highly skilled domain expert teams and data scientists. Nevertheless, the accuracy of manual fraud detection methodologies are low and due to that, it is very difficult to handle large volumes of data. More often, it requires time-consuming investigations into the other transactions related to the fraudulent activity in order to identify fraudulent activity patterns. Finance companies are not getting adequate return of interest (ROI) despite the resources and money spent on these traditional methodologies. Most of the traditional fraud detection methodologies focused on discrete data points. (User accounts, IP addresses devices, etc...) However, these methodologies are no longer sufficient for today's needs. As fraudsters and hackers are using more advanced and cutting edge techniques to mask their fraudulent activities even from the sharpest eyes. These methodologies can only detect known types of attacks, therefore an analytical approach is required to address these drawbacks of the traditional methodologies.
The aim of this paper is to review selected machine learning and outlier detection techniques that can be integrated into a fraud detection system for financial transactions. Various machine-learning algorithms such as Bayesian Networks, Recurrent Neural Networks, Support Vector Machines, Fuzzy Logic, Hidden Markov Model, K-Means Clustering, K-Nearest Neighbor and their existing implementations on fraud detection domain will be discussed to find a better approach for a fraud detection system.
- Oxford Dictionary, "fraud | Definition of fraud in English by Oxford Dictionaries." {Online}. Available: https://en.oxforddictionaries.com/definition/fraud. {Accessed: 12-Nov-2017}.Google Scholar
- Central Intelligence Agency, "The World Factbook," 2016. {Online}. Available: https://www.cia.gov/library/publications/the-world-factbook/geos/xx.html. {Accessed: 10-Oct-2017}.Google Scholar
- Association of Certified Fraud Examiners, "ACFE Report Estimates Organizations Worldwide Lose 5 Percent of Revenues to Fraud," 2012.Google Scholar
- Trading Economics, "Sri Lanka GDP Growth Rate," 2017. {Online}. Available: tradingeconomics.com/sri-lanka/gdp-growth. {Accessed: 10-Oct-2017}.Google Scholar
- Kroll, "Global Fraud Report: Vulnerabilities on the Rise," 2015.Google Scholar
- Maxwell Locke & Ritter, "Which industries are hardest hit by fraud?," MLR, 2016. {Online}. Available: http://www.mlrpc.com/articles/which-industries-are-hardest-hit-by-fraud/. {Accessed: 10-Oct-2017}.Google Scholar
- Telegraph, "Three UK men arrested over $200m credit card fraud," 05-Jun-2013.Google Scholar
- BBC, "Men jailed over fake credit cards," 29-Oct-2008.Google Scholar
- M. Evans, "Hackers steal £650 million in world's biggest bank raid - Telegraph," 15-Feb-2015. {Online}. Available: http://www.telegraph.co.uk/news/uknews/crime/11414191/Hackers-steal-650-million-in-worlds-biggest-bank-raid.html. {Accessed: 10-Dec-2017}.Google Scholar
- S. Mukherjee, F# for Machine Learning Essentials. Packt Publishing Ltd, 2016.Google Scholar
- G. Tang, J. Pei, J. Bailey, and G. Dong, Mining Multidimensional Contextual Outliers from Categorical Relational Data *.Google Scholar
- S. Omar, A. Ngadi, and H. H. Jebur, Machine Learning Techniques for Anomaly Detection: An Overview. 2013.Google Scholar
- N. Goernitz, M. M. Kloft, K. Rieck, and U. Brefeld, "Toward Supervised Anomaly Detection," ArXiv14016424 Cs, Jan. 2014. Google ScholarDigital Library
- P. Srinath, "Introduction to Anomaly Detection: Concepts and Techniques | My views of the World and Systems," 2016. {Online}. Available: https://iwringer.wordpress.com/2015/11/17/anomaly-detection-concepts-and-techniques/. {Accessed: 10-Oct-2017}.Google Scholar
- D. Heckerman, "A Tutorial on Learning With Bayesian Networks," Mar. 1995.Google Scholar
- S. Maes, K. Tuyls, B. Vanschoenwinkel, and B. Manderick, "Credit Card Fraud Detection. Applying Bayesian and Neural networks," Oct. 2017.Google Scholar
- L. Mukhanov, "Using Bayesian Belief Networks for credit card fraud detection," 2008, pp. 221--225. Google ScholarDigital Library
- B. Wiese and C. Omlin, "Credit Card Transactions, Fraud Detection, and Machine Learning: Modelling Time with LSTM Recurrent Neural Networks," vol. 247, 1970, pp. 231--268.Google Scholar
- D. Abdelhamid, S. Khaoula, and O. Atika, Automatic Bank Fraud Detection Using Support Vector Machines.Google Scholar
- Y. Sahin and E. Duman, "Detecting Credit Card Fraud by Decision Trees and Support," in Vector Machines", International Multiconference of Engineers and computer scientists, 2011.Google Scholar
- P. Alam and M. Lenard, "Application of Fuzzy Logic to Fraud Detection," Jan. 2009.Google Scholar
- T. Razooqi, P. Khurana, K. Raahemifar, and A. Abhari, "Credit Card Fraud Detection Using Fuzzy Logic and Neural Network," in Proceedings of the 19th Communications & Networking Symposium, San Diego, CA, USA, 2016, p. 7:1--7:5. Google ScholarDigital Library
- P. Bentley, "Fuzzy Darwinian Detection of Credit Card Fraud - Semantic Scholar," 2004. {Online}. Available: /paper/Fuzzy-Darwinian-Detection-of-Credit-Card-Fraud-Bentley/364c45aeacd872370d0dab30456afa11f0ccc23c. {Accessed: 19-Jan-2018}.Google Scholar
- M. W. Kadous, M. W. Kadous, and S. C. Sammut, "Temporal Classification: Extending the Classification Paradigm to Multivariate Time Series," The University of New South Wales, 2002.Google Scholar
- J. Brownlee, "Supervised and Unsupervised Machine Learning Algorithms," Machine Learning Mastery, 16-Mar-2016.Google Scholar
- M. Goldstein and A. Dengel, Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm.Google Scholar
- B. Baesens, V. V. Vlasselaer, and W. Verbeke, Fraud Analytics Using Descriptive, Predictive, and Social Network Techniques: A Guide to Data Science for Fraud Detection, 1st ed. Wiley Publishing, 2015. Google ScholarDigital Library
- P. Filzmoser and K. Hron, "Outlier detection for compositional data using robust methods," Math. Geosci., pp. 233--248, 2008.Google Scholar
- T. Chetcuti and A. Dingli, "Using Hidden Markov Models in Credit Card Transaction Fraud Detection," 2018.Google Scholar
- K. R. Sungkono and R. Sarno, "Patterns of fraud detection using coupled Hidden Markov Model," in 2017 3rd International Conference on Science in Information Technology (ICSITech), 2017, pp. 235--240.Google Scholar
- J. McCaffrey, "Data Clustering - Detecting Abnormal Data Using k-Means Clustering," Feb-2013. {Online}. Available: https://msdn.microsoft.com/en-us/magazine/jj891054.aspx?f=255&MSPPError=-2147217396. {Accessed: 20-Feb-2018}.Google Scholar
- K. Davenport, "The Cost Function of K-Means," Kevin Davenport, 14-Feb-2014.Google Scholar
- X. Meiping, "Application of Bayesian Rules Based on Improved K-Means Cassification on Credit Card," in 2009 International Conference on Web Information Systems and Mining, 2009, pp. 13--16. Google ScholarDigital Library
- A. Weerathunga, "{Article} Anomaly Detection Using K-Means Clustering," 06-Jan-2016. {Online}. Available: https://wso2.com/library/articles/2016/01/article-anomaly-detection-using-k-means-clustering/. {Accessed: 01-Nov-2017}.Google Scholar
- L. D. Angelo and L. Giaccari, "An efficient algorithm for the nearest neighbourhood search for point clouds," 2011.Google Scholar
- M. Goldstein and A. Dengel, "Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm - Semantic Scholar," 2012. {Online}. Available: /paper/Histogram-based-Outlier-Score-HBOS-A-fast-Unsuperv-Goldstein-Dengel/5cf881d1db19834f123fcfc79ad32097aeafe17f. {Accessed: 12-Nov-2017}.Google Scholar
- M. Leung, "k-Nearest Neighbor Algorithm for Classification," 13-Nov-2007.Google Scholar
- S. Fernando, "Fraud Detection and Prevention: A Data Analytics Approach," 2015. {Online}. Available: http://wso2.com/whitepapers/fraud-detection-and-prevention-a-data-analytics-approach/. {Accessed: 10-Oct-2017}.Google Scholar
- F. Lu, J. Boritz, and D. Covvey, "Adaptive Fraud Detection Using Benford's Law," 2006, vol. 4013, pp. 347--358. Google ScholarDigital Library
Index Terms
- Critical Analysis of Machine Learning Based Approaches for Fraud Detection in Financial Transactions
Recommendations
Fraud detection in credit card transaction using neural networks
SCA '19: Proceedings of the 4th International Conference on Smart City ApplicationsBanking transactions, such as online transactions, credit card transactions and the mobile wallet, are gaining popularity. People are shopping more and more using credit cards. Credit cards have become a necessity, to the virtual world, for digitized ...
A comparison of machine learning algorithms for credit card fraud detection
NISS '23: Proceedings of the 6th International Conference on Networking, Intelligent Systems & SecurityWith the increasing use of credit cards for online and offline transactions, the risk of fraudulent activities has also increased significantly. In this study, we propose a machine learning-based approach to predict credit card fraud. We used a public ...
Research on Credit Card Fraud Detection Model Based on Distance Sum
JCAI '09: Proceedings of the 2009 International Joint Conference on Artificial IntelligenceAlong with increasing credit cards and growing trade volume in China, credit card fraud rises sharply. How to enhance the detection and prevention of credit card fraud becomes the focus of risk control of banks. This paper proposes a credit card fraud ...
Comments