Total views : 349

An Efficient Misclassification Cost Concerned Imbalanced Class Handling to Improve the Financial Fraud Detection Scheme


  • Department of Computer Science, Karpagam University, Coimbatore – 641021, Tamil Nadu, India
  • Department of Computer Science, Sri Sarada College for Women, Salem – 636016, Tamil Nadu, India


Objective: Financial fraud detection is the most concerned task in many of the real world application where the number of fraudulent transaction is occurring. The efficient handling of the imbalanced financial data set would lead to the accurate and improved prediction of the more fraudulent behaviour present in the financial system. Method: An Optimal Ensemble Classification using PSO (OEC-PSO) is introduced. In our previous research work, Forecasting of Automatic Relevance Determination and Ripper classification (FARD-RIPPER) approach has been suggested which would classify the relevant subset of features that are more relevant to each other using ripper classification approach. However single base classifier used for classification might lead to the high misclassification rate which is resolved in the proposed research work. OEC-PSO makes use of four different classifiers namely, "ADTree, Cart, Prism and Ripper" for Assembling to obtain accurate classification result. Particle swarm optimization approach is introduced in this work for selecting the most optimal ensemble classifier which can produce the accurate classification result. The fitness value is updated in the every iteration by randomly changing the combination of classifiers and the subset features from training data partitions. Final Ensembling result is obtained by fusing the different classifiers results using weighted average scheme. The overall flow of this work provides flexible way for the users to detect the fraudulent behaviours present in the financial transaction system in terms of malicious patterns. Findings: The experimental tests were conducted in the Matlab simulation environment in terms of various performance metrics to prove the improvement of the proposed approach. The various performance metrics that are considered in this work are accuracy, precision, misclassification cost and the computational complexity. The experimental tests were conducted between the proposed methodology named "OEC-PSO" and the existing work called the Cost Sensitive Classification Method (CSCM). The results obtained were proved that the proposed methodology can work well with the improved accuracy, misclassification cost and the precision rate. Application/Improvements: The finding of this work demonstrates that the proposed methodology provides better result than the existing work in terms of improved accuracy and the computational procedure. It can be applied in the various online transaction oriented application such as banking, insurance sector and so on.


Fraud Detection, Misclassification Cost, Subset Selection, Sphere Cover Approach.

Full Text:

 |  (PDF views: 185)


  • Dheepa V, Dhanapal R. Behavior based credit card fraud detection using support vector machines. ICTACT Journal on Soft Computing. 2012; 4:391–7.
  • Patidar R, Sharma L. Credit card fraud detection using neural network. IJSCE. 2011; 1(NCAI2011):32–8.
  • Ngai EWT, Hu Y, Wong YH, Chen Y, Sun X. The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision Support System. 2010; 50(3):559-69
  • Seeja KR, Zareapoor M. Fraud miner: A novel credit card fraud detection model based on frequent item set mining. The Scientific World Journal. 2014:10.
  • Srivastava A, Kundu A, Majumdar AK. Credit card fraud detection using hidden markov model. IEEE Transactions on Dependable and Secure Computing. 2008; 5(1): 37–48.
  • Prakash A, Chandrasekar C. An optimized multiple semi-hidden Markova model for credit card fraud detection. Indian Journal of Science and Technology. 2015; 8(2):165–71
  • Khan AUS, Akhtar N, Qureshi MN. Real-time credit-card fraud detection using artificial neural network tuned by simulated annealing algorithm. Proceedings of International Conference on Recent Trends in Information, Telecommunication and Computing, ITC; 2014. p. 113-21.
  • Ogwueleka FN. Data mining application in credit card fraud detection system. Journal of Engineering Science and Technology. 2011; 6(3):311–22.
  • Quah JTS, Sri Ganesh M. Real-time credit card fraud detection using computational intelligence. Expert Systems with Applications. 2008; 35(4):1721–32.
  • Zaslavsky V, Strizhak A. Credit card fraud detection using self-organizing maps. Information and Security. 2006; 18:48–63.
  • Manoharan GV, Shanmugalakshmi R. Multi-objective firefly algorithm for multi-class gene selection. Indian Journal of Science and Technology. 2015 Jan; 8(1). Doi no:10.17485/ijst/2015/v8i1/52310
  • Gayathri C, Umarani R. Forecasting of Automatic Relevance Determination for Feature Selection (FARD-FS) in financial fraud detection. Malaysian Journal of Computer Science.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.