Abstract
Fraud detection has been a difficult problem in the industry for the past many years which has caused a massive financial loss for individuals/organizations. Machine learning techniques have proved to be an efficient technique to identify and detect fraud. The major problem which exists in this domain is “Concept drift”. Fraudsters tend to evolve their habits over time which eventually leads to a pattern change. Machine learning models normally depend on the reliable set of labels which classifies whether the transaction is fraud or legitimate. When there happens a change in the patterns, the model tends to lose its performance in predicting new patterns. A model which adapt to this changing behaviour is inevitable in such scenarios. In this paper, we have reviewed several articles which discusses the problem of concept drift in fraud detection, and we have also surveyed different types of methods and techniques used so far by the researchers to deal with it. Above that the paper also proposes a procedure and steps to make a machine learning model adaptive.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Laleh N, Abdollahi Azgomi M (2009) A taxonomy of frauds and fraud detection techniques. Commun Comput Inf Sci 31:256–267
Li J, Huang K-Y, Jin J, Shi J (2008) A survey on statistical methods for health care fraud detection. Health Care Manag Sci 11(3):275–287
Bolton RJ, Hand DJ, Provost F, Breiman L, Bolton RJ, Hand DJ (2002) Statistical fraud detection: a review. Stat Sci 17(3):235–255
Gama J, Zliobaite I, Bifet A, Pechenizkiy M, Bouchachia A (2014) “A survey on concept drift adaptation,” ACM Comput Surv 46(4)
Žliobaitė I (2010) “Learning under concept drift: an overview,” Tech Report Fac Math Informatics, 1–36
Schoen C et al (2012) A survey of primary care doctors in ten countries shows progress in use of health information technology, less in other areas. Health Aff 31(12):2805–2816
Sahin Y, Duman E (2011) “IMECS2011_pp442–447,” I
Control F, Industry HC (1996) “National Institute of Justice”
Khamassi I, Moez MS (2015) “Self-adaptive windowing approach for handling complex concept drift”. Cogn Comput, Springer, 7:772–790
Schlimmer JC, Granger RH (1986) Incremental learning from noisy data. Mach Learn 1(3):317–354
Widmer G (1996) Learning in the presence of concept drift and hidden contexts. Mach Learn 23(1):69–101
Salganicoff M (1997) Tolerating concept and sampling shift in lazy learning using prediction error context switching. Artif Intell Rev 11(1–5):133–155
Nick Street W, Kim YS (2001) “A streaming ensemble algorithm (SEA) for large-scale classification,” Proc Seventh ACM SIGKDD Int Conf Knowl Discov Data Min no. June, pp 377–382
Kolter JZ, Maloof MA (2007) Dynamic weighted majority: an ensemble method for drifting concepts. J Mach Learn Res 8:2755–2790
Tsymbal A (2004) “The problem of concept drift: definitions and related work,” Comput Sci Dep Trinity Coll Dublin, no. May
Jog A, Chandavale AA (2018) Implementation of credit card fraud detection system with concept drifts adaptation. Adv Intell Syst Comput 673:467–477
Ghomeshi H, Gaber MM, Kovalchuk Y (2019) EACD: evolutionary adaptation to concept drifts in data streams. Data Min Knowl Discov 33(3):663–694
Sun Y, Wang Z, Bai Y, Dai H, Nahavandi S (2018) “A classifier graph-based recurring concept detection and prediction approach.” Comput Intell Neurosci 2018
Harel M, Crammer K, El-Yaniv R, Mannor S (2014) “Concept drift detection through resampling,” 31st Int Conf Mach Learn. ICML 2014, 3:2682–2694
Priya S, Uthra RA (2020) “Comprehensive analysis for class imbalance data with concept drift using ensemble-based classification.” J Ambient Intell Humaniz Comput 0123456789
Khamassi I, Sayed-Mouchaweh M, Hammami M, Ghédira K (2013) “Ensemble classifiers for drift detection and monitoring in dynamical environments,” PHM 2013—Proc Annu Conf Progn Heal Manag Soc, 199–212
Dietterich TG (2000) “Ensemble methods in machine learning,” Lect Notes Comput Sci (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), 1857 LNCS, 1–15
Scholz M, Klinkenberg R (2014) “An ensemble classifier for drifting concepts an ensemble classifier for drifting concepts,” no. May
Krawczyk B, Minku LL, Gama J, Stefanowski J, Woźniak M (2017) Ensemble learning for data stream analysis: a survey. Inf Fusion 37:132–156
Escovedo T, Da Cruz AVA, Vellasco MMBR, Koshiyama AS (2013) Learning under concept drift using a neuro-evolutionary ensemble. Int J Comput Intell Appl 12(4):1–16
Silva B, Marques N, Panosso G (2012) Applying neural networks for concept drift detection in financial markets. CEUR Workshop Proc 960:43–47
Najafi M, “Incremental learning of ANN in the presence of concept drift”
e outros MGA, Castillo PA (2001) “Artificial neural networks design using evolutionary algorithms”
Widrow B, Lehr MA (1993) Adaptive neural networks and their applications. Int J Intell Syst 8(4):453–507
Fortin FA, De Rainville FM, Gardner MA, Parizeau M, Gagńe C (2012) DEAP: evolutionary algorithms made easy. J Mach Learn Res 13:2171–2175
Padmalatha E, Reddy CRK, Padmaja B (2015) Classification of concept-drifting data streams using optimized genetic algorithm. Int J Comput Appl 125(15):1–6
Smith M, Ciesielski V (2016) “Adapting to concept drift with genetic programming for classifying streaming data,” 2016 IEEE Congr Evol Comput CEC 2016, pp 5026–5033
A. N. Sloss and S. Gustafson, “2019 Evolutionary Algorithms Review,” pp. 307–344, 2020.
Pozzolo AD, Boracchi G, Caelen O, Alippi C, Bontempi G“Credit card fraud detection and concept-drift adaptation with delayed supervised information”
Lu F, Boritz JE, Covvey D (2006) Adaptive fraud detection using Benford’s law. Adv Artif Intell Proc 4013:347–358
Somasundaram A, Reddy S (2019) Parallel and incremental credit card fraud detection model to handle concept drift and data imbalance. Neural Comput Appl 31:3–14
Chen CH, Li Y, Hong TP, Li YK, Lu EHC (2015) “A GA-based approach for mining membership functions and concept-drift patterns,” 2015 IEEE Congr Evol Comput CEC 2015—Proc. no. May, pp 2961–2965
Lu N, Zhang G, Lu J (2014) Concept drift detection via competence models. Artif Intell 209(1):11–28
Elwell R, Polikar R (2011) Incremental learning of concept drift in nonstationary environments. IEEE Trans Neural Networks 22(10):1517–1531
Mao H, Liu Y (2018) “Adaptive fraud detection system using dynamic risk features,” no. October
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shamitha, S.K., Ilango, V. (2022). Importance of Self-Learning Algorithms for Fraud Detection Under Concept Drift. In: Sanyal, G., Travieso-González, C.M., Awasthi, S., Pinto, C.M., Purushothama, B.R. (eds) International Conference on Artificial Intelligence and Sustainable Engineering. Lecture Notes in Electrical Engineering, vol 837. Springer, Singapore. https://doi.org/10.1007/978-981-16-8546-0_28
Download citation
DOI: https://doi.org/10.1007/978-981-16-8546-0_28
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8545-3
Online ISBN: 978-981-16-8546-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)