EcomFraudEX: An Explainable Machine Learning Framework for Victim-Centric and Dual-Sided Fraud Incident Classification in E-Commerce

Salman Farsi; Mahfuzulhoq Chowdhury

doi:10.4108/eetsis.6789

Authors

Salman Farsi Chittagong University of Engineering & Technology
Mahfuzulhoq Chowdhury Chittagong University of Engineering & Technology

DOI:

https://doi.org/10.4108/eetsis.6789

Keywords:

Fraud Detection, Fraud Prevention, E-Commerce, Explainable AI, Ensemble Majority Voting, Survey Data, Feature Selection

Abstract

The popularity of e-commerce businesses and online shopping is experiencing rapid growth all around the world. Nowadays, people are more inclined to shop online than in the actual shops. Due to this advancement, fraudsters have set new traps to deceive consumers. Whether it is true that customers often become victims of fraud, it also happens that a fraud customer tries to deceive the seller and hassle the seller intentionally in several ways. To address these issues, an automated system is required so that fraud incidents can be classified. This will facilitate taking legal action and reporting to consumer rights authorities. Existing research on fraud detection and prevention didn't cover customer and seller-side fraud simultaneously. Besides, most of the work focused on fraud detection rather than post-fraud incident classification. To overcome these gaps, this research endeavor conducts a thorough online survey of customers and sellers to gather incident-specific victim data on fraud cases and it addresses the issue for both customer and seller. This paper proposes a machine learning (ML) based explainable fraud incident classification framework EcomFraudEX, that can efficiently classify these fraud incidents and analyze the reason behind each incident. This framework particularly focuses on proper feature selection techniques, hyper-parameter tuning of models, and exploring different ML and ensemble models. Ensemble majority voting schemes consisting of Random Forest (RF), XGBoost, and CatBoost achieved the highest F1-score of 96% with the Chi-Square feature selection technique in the customer complaint dataset and 98% with the RF feature selection technique in the seller complaint dataset. To explain the incident reasoning, Local Interpretable Model Agnostic Explanation (LIME) and Shapely Additive Explanation (SHAP) were further utilized. The proposed scheme achieved a 1.57% higher F1-score and 2.13% higher accuracy than previous works.

References

[1] E-Commerce Fraud Statistics: $48 Billion Lost Annually | wisernotify.com [Internet]. [Accessed: 2024 Jun 13]. Available from: https://wisernotify.com/blog/ecommerce-fraud-stats/

[2] 23+ eCommerce Fraud Statistics (2024) [Internet]. [Accessed: 2024 Jun 13]. Available from: https://explodingtopics.com/blog/ecommerce-fraud-stats

[3] Ileberi E, Sun Y, Wang Z. A machine learning based credit card fraud detection using the GA algorithm for feature selection. J Big Data. 2022 Dec 25;9(1):24.

[4] Karunachandra B, Putera N, Wijaya SR, Suryani D, Wesley J, Purnama Y. On the benefits of machine learning classification in cashback fraud detection. Procedia Comput Sci. 2023;216:364–9.

[5] Hu X, Zhang X, Lovrich NP. Forecasting Identity Theft Victims: Analyzing Characteristics and Preventive Actions through Machine Learning Approaches. Vict Offender. 2021 May 19;16(4):465–94.

[6] Nguyen NT, Ha PP, Nguyen LT, Nguyen KV, Nguyen NL. Vietnamese complaint detection on e-commerce websites. In New Trends in Intelligent Software Methodologies, Tools and Techniques 2021 (pp. 618-629). IOS Press.

[7] Sabih M, Ejaz M, Quershi KK, Asad MU, Gu J, Balas VE, et al. Fraud Prediction in Pakistani E-commerce Market. In: 2021 4th International Symposium on Advanced Electrical and Communication Technologies (ISAECT). IEEE; 2021. p. 01–6.

[8] Ramadhan, Ghaniaviyanto N, Putrada, Gautama A. XGBoost for Predicting Airline Customer Satisfaction Based on Computational Efficient Questionnaire. International Journal on Information and Communication Technology (IJoICT). 2023;9(2):120–36.

[9] Seera M, Lim CP, Kumar A, Dhamotharan L, Tan KH. An intelligent payment card fraud detection system. Ann Oper Res. 2024 Mar 8;334(1–3):445–67.

[10] Alzahrani RA, Aljabri M. AI-Based Techniques for Ad Click Fraud Detection and Prevention: Review and Research Directions. Journal of Sensor and Actuator Networks. 2022 Dec 31;12(1):4.

[11] BOZYİĞİT F, DOĞAN O, KILINÇ D. Categorization of Customer Complaints in Food Industry Using Machine Learning Approaches. Journal of Intelligent Systems: Theory and Applications. 2022 Mar 1;5(1):85–91.

[12] Vu T, Nguyen DQ, Nguyen DQ, Dras M, Johnson M. VnCoreNLP: A Vietnamese natural language processing toolkit. arXiv preprint arXiv:1801.01331. 2018 Jan 4.

[13] Whittaker JM, Edwards M, Cross C, Button M. “I Have Only Checked after the Event”: Consumer Approaches to Safe Online Shopping. Vict Offender. 2023 Oct 3;18(7):1259–81.

[14] Cohen J. Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. Psychol Bull. 1968;70(4):213–20.

[15] LabelEncoder - scikit-learn 1.5.0 documentation [Internet]. [Accessed: 2024 Jun 13]. Available from: https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.LabelEncoder.html

[16] Alshaer HN, Otair MA, Abualigah L, Alshinwan M, Khasawneh AM. Feature selection method using improved CHI Square on Arabic text classifiers: analysis and application. Multimed Tools Appl. 2021 Mar 21;80(7):10373–90.

[17] Menze BH, Kelm BM, Masuch R, Himmelreich U, Bachert P, Petrich W, et al. A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinformatics. 2009 Dec 10;10(1):213.

[18] Hosmer Jr DW, Lemeshow S, Sturdivant RX. Applied logistic regression. John Wiley & Sons; 2013.

[19] Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intelligent Systems and their Applications. 1998 Jul;13(4):18–28.

[20] Peterson LE. K-nearest neighbor. Scholarpedia. 2009;4(2):1883.

[21] Quinlan JR. Induction of decision trees. Machine learning. 1986 Mar;1:81-106.Breiman L. Random forests. Mach Learn. 2001;45:5–32.

[22] Chen T, Guestrin C. XGBoost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY, USA: ACM; 2016. p. 785–94.

[23] Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst. 2018;31.

[24] Freund Y, Schapire RE. A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. J Comput Syst Sci. 1997 Aug;55(1):119–39.

[25] Eusha A, Farsi S, Islam A, Hossain J, Ahsan S, Hoque MM. CUET_Binary_Hackers@DravidianLangTech-EACL 2024: Sentiment Analysis using Transformer-Based Models in Code-Mixed and Transliterated Tamil and Tulu. In: Chakravarthi BR, Priyadharshini R, Madasamy AK, Thavareesan S, Sherly E, Nadarajan R, et al., editors. Proceedings of the Fourth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages [Internet]. St. Julian’s, Malta: Association for Computational Linguistics; 2024. p. 205–11. Available from: https://aclanthology.org/2024.dravidianlangtech-1.34

[26] Van den Broeck G, Lykov A, Schleich M, Suciu D. On the Tractability of SHAP Explanations. Journal of Artificial Intelligence Research. 2022 Jun 23;74:851–86.

[27] Vishwarupe V, Joshi PM, Mathias N, Maheshwari S, Mhaisalkar S, Pawar V. Explainable AI and Interpretable Machine Learning: A Case Study in Perspective. Procedia Comput Sci. 2022;204:869–76.

[28] Zhang Y, Wang J, Zhang X. Personalized sentiment classification of customer reviews via an interactive attributes attention model. Knowledge-Based Systems. 2021 Aug 17;226:107135.