Skip to main content

Advertisement

SpringerLink
Log in

Performance analysis of metaheuristics based hyperparameters optimization for fraud transactions detection

  • Research Paper
  • Published:
Evolutionary Intelligence Aims and scope Submit manuscript

Abstract

In recent years, detecting fraud transactions has become a popular research topic because credit card fraud transactions result in the loss of billions of dollars every year. Therefore, the need for financial institutions and banks to improve their fraud detection systems is increasing. Financial institutions are increasingly using data mining to develop fraud detection systems that can detect and stop fraudulent transactions automatically. From the standpoint of machine learning, detecting fraud transactions is a binary classification problem. However, interpretability is essential for management to have faith in the used model and to develop fraud prevention strategies. Designing an algorithm that can detect fraud transactions is difficult and needs a higher understanding of each part of the process and a lot of time. However, hyperparameters optimization using metaheuristics techniques reduces the understanding and time needed to handle this issue. Hyperparameters optimization is a technique that is used to select the best hyperparameters that yield the highest performance. Using a metaheuristic approach has many advantages, such as improving the performance of the machine learning model,Tayebi e facilitating the usage of the machine learning model, etc. Our proposed solution in this work is to use metaheuristic algorithms such as genetic algorithms (GA), differential evolution (DE), artificial bee colony algorithm (ABC), grey wolf optimizer algorithm (GWO), particle swarm optimization (PSO), and teaching learning-based optimization (TLBO), to optimize hyperparameters and compare these algorithms with grid search method (GS). The used machine learning models in this study are AdaBoost (AD), random forest (RF), logistic regression (LR), support vector machine classifier (SVM), k-nearest neighbors (KNN), mlpclassier (MLP), and decision tree (DT). To compare these optimizers, we use the following evaluation metrics; accuracy, recall, f1-score, precision, and the area under the roc curve (AUC).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References

  1. Saia R, Carta S (2019) Evaluating the benefits of using proactive transformed-domain-based techniques in fraud detection tasks. Future Gener Comput Syst 93:18–32

    Article  Google Scholar 

  2. Yazdinejad A, Dehghantanha A, Parizi RM, Hammoudeh M, Karimipour H, Srivastava G (2022) Block hunter: federated learning for cyber threat hunting in blockchain-based IIoT networks. IEEE Trans Ind Inform. https://doi.org/10.1109/TII.2022.3168011

    Article  Google Scholar 

  3. Feurer M, Hutter F (2019) Hyperparameter optimization. Automated machine learning. Springer, Berkeley, pp 3–33

    Chapter  Google Scholar 

  4. Claesen M, De Moor B (2015) Hyperparameter search in machine learning, Agadir, June 7–10, pp 1–5. https://doi.org/10.48550/arXiv.1502.02127

  5. Yang L, Shami A (2020) On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415:295–316

    Article  Google Scholar 

  6. Lucas Y, Portier P-E, Laporte L, He-Guelton L, Caelen O, Granitzer M, Calabretto S (2020) Towards automated feature engineering for credit card fraud detection using multi-perspective HMMs. Future Gener Comput Syst 102:393–402

    Article  Google Scholar 

  7. Turner R, Eriksson D, McCourt M, Kiili J, Laaksonen E, Xu Z, Guyon I (2021) Bayesian optimization is superior to random search for machine learning hyperparameter tuning: analysis of the black-box optimization challenge 2020. In: NeurIPS 2020 competition and demonstration track. PMLR, pp 3–26

  8. Bandaru S, Deb K (2016) Metaheuristic techniques. Decis Sci 220(4598):693–750

    Article  Google Scholar 

  9. Gendreau M, Potvin J-Y et al (2010) Handbook of metaheuristics, vol 2. Springer, New York, p 9. https://doi.org/10.1007/978-1-4419-1665-5

    Book  Google Scholar 

  10. Ngai EW, Hu Y, Wong YH, Chen Y, Sun X (2011) The application of data mining techniques in financial fraud detection: a classification framework and an academic review of literature. Decis Support Syst 50(3):559–569

    Article  Google Scholar 

  11. Awoyemi JO, Adetunmbi AO, Oluwadare SA (2017) Credit card fraud detection using machine learning techniques: a comparative analysis. In: 2017 international conference on computing networking and informatics (ICCNI). IEEE, pp 1–9

  12. Belhadi A, Djenouri Y, Srivastava G, Djenouri D, Cano A, Lin JC-W (2020) A two-phase anomaly detection model for secure intelligent transportation ride-hailing trajectories. IEEE Trans Intell Transp Syst 22(7):4496–4506

    Article  Google Scholar 

  13. Tayebi M, El Kafhali S (2021) Hyperparameter optimization using genetic algorithms to detect frauds transactions. In: The international conference on artificial intelligence and computer vision. Springer, pp 288–297

  14. Li Z, Huang M, Liu G, Jiang C (2021) A hybrid method with dynamic weighted entropy for handling the problem of class imbalance with overlap in credit card fraud detection. Expert Syst Appl 175:114750. https://doi.org/10.1016/j.eswa.2021.114750

    Article  Google Scholar 

  15. Hussein AS, Khairy RS, Najeeb SMM, ALRikabi HT et al (2021) Credit card fraud detection using fuzzy rough nearest neighbor and sequential minimal optimization with logistic regression. Int J Interact Mob Technol 15(5):24–42

    Article  Google Scholar 

  16. Sudha C, Akila D (2021) Majority vote ensemble classifier for accurate detection of credit card frauds. Mater Today Proc. https://doi.org/10.1016/j.matpr.2021.01.616

    Article  Google Scholar 

  17. Asha R, KR SK (2021) Credit card fraud detection using artificial neural network. Glob Transit Proc 2(1):35–41

    Article  Google Scholar 

  18. Baesens B, Höppner S, Verdonck T (2021) Data engineering for fraud detection. Decis Support Syst 150:113492. https://doi.org/10.1016/j.dss.2021.113492

    Article  Google Scholar 

  19. Mishra KN, Pandey SC (2021) Fraud prediction in smart societies using logistic regression and k-fold machine learning techniques. Wirel Pers Commun 119(2):1341–1367

    Article  Google Scholar 

  20. Salah K, El Kafhali S (2017) Performance modeling and analysis of hypoexponential network servers. Telecommun Syst 65(4):717–728

    Article  Google Scholar 

  21. Lenka SR, Barik RK, Patra SS, Singh VP (2021) Modified decision tree learning for cost-sensitive credit card fraud detection model. Advances in communication and computational technology. Springer, New York, pp 1479–1493

    Chapter  Google Scholar 

  22. Arya M, Sastry GH (2020) Deal—‘deep ensemble algorithm’ framework for credit card fraud detection in real-time data stream with google tensorflow. Smart Sci 8(2):71–83

    Article  Google Scholar 

  23. Carcillo F, Le Borgne Y-A, Caelen O, Kessaci Y, Oblé F, Bontempi G (2021) Combining unsupervised and supervised learning in credit card fraud detection. Inf Sci 557:317–331

    Article  MathSciNet  Google Scholar 

  24. Zhu H, Liu G, Zhou M, Xie Y, Abusorrah A, Kang Q (2020) Optimizing weighted extreme learning machines for imbalanced classification and application to credit card fraud detection. Neurocomputing 407:50–62

    Article  Google Scholar 

  25. Wang C, Han D (2019) Credit card fraud forecasting model based on clustering analysis and integrated support vector machine. Clust Comput 22(6):13861–13866

    Article  Google Scholar 

  26. Rtayli N, Enneya N (2020) Selection features and support vector machine for credit card risk identification. Procedia Manuf 46:941–948

    Article  Google Scholar 

  27. Huang K (2020) An optimized LightGBM model for fraud detection. J Phys Conf Ser 1651:012111

    Article  Google Scholar 

  28. Wolsey LA, Nemhauser GL (1999) Integer and combinatorial optimization, vol 55. John Wiley & Sons

  29. Du Ke-Lin SM (2016) Search and optimization by metaheuristics, techniques and algorithms inspired by nature. Springer, New York. https://doi.org/10.1007/978-3-319-41192-7

    Book  Google Scholar 

  30. Patel RD, Singh DK (2013) Credit card fraud detection & prevention of fraud using genetic algorithm. Int J Soft Comput Eng 2(6):292–294

    Google Scholar 

  31. Clerc M (2010) Particle swarm optimization, vol 93. Wiley, Newport Beach. https://doi.org/10.1002/9780470612163

    Book  Google Scholar 

  32. Tayebi M, El Kafhali S (2022) Deep neural networks hyperparameter optimization using particle swarm optimization for detecting frauds transactions. Advances on smart and soft computing. Springer, Casablanca, pp 507–516

    Chapter  Google Scholar 

  33. Karaboga D, Basturk B (2008) On the performance of artificial bee colony (ABC) algorithm. Appl Soft Comput 8(1):687–697

    Article  Google Scholar 

  34. Lampinen J, Storn R (2004) Differential evolution. New optimization techniques in engineering. Springer, New York, pp 123–166

    Chapter  Google Scholar 

  35. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61

    Article  Google Scholar 

  36. Venkata Rao R (2004) Teaching-learning-based optimization algorithm. New optimization techniques in engineering. Springer, Cham, pp 123–166

    Google Scholar 

  37. Kaggle. https://www.kaggle.com/mlg-ulb/creditcardfraud. Accessed 30 June 2021

  38. Vermeulen AF (2020) Unsupervised learning: deep learning. Industrial machine learning. Springer, New York, pp 225–241

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Sciences and Techniques, Computer, Networks, Modeling, and Mobility Laboratory (IR2M), Hassan First University of Settat, 26000, Settat, Morocco

    Mohammed Tayebi & Said El Kafhali

Authors
  1. Mohammed Tayebi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Said El Kafhali
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Said El Kafhali.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tayebi, M., El Kafhali, S. Performance analysis of metaheuristics based hyperparameters optimization for fraud transactions detection. Evol. Intel. 17, 921–939 (2024). https://doi.org/10.1007/s12065-022-00764-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12065-022-00764-5

Keywords

Search

Navigation