Abstract:
In an era characterized by extensive credit use and rapidly advancing technology, mitigating fraud in online transactions is more critical than ever. This paper presents a systematic literature review (SLR) on applying Machine Learning Methods in fraud detection in online shopping.In addition, a comparative analysis of a more comprehensive array of Machine Learning techniques, including Logistic Regression,
Decision Tree, Random Forest, SVM, KNN, and Neural Networks with CNN, ANN, Transformers, and Autoencoder, were applied to detect fraud in the heavily imbalanced dataset provided by IEEE-CIS[1], a common characteristic in real-world fraud detection scenarios.This study explores the limitations, opportunities, and challenges ofapplying these machine learning models in detecting credit card fraud in e-commerce, shedding light on the significant potential and current limitations of such approaches.
Our comparative analysis found that the Random Forest algorithm also demonstrated robust performance, attaining a close accuracy of 95,5%.Interestingly, the Transformers utilizing the pre-traineddistilbert-base-uncased model achieved the highest performance, reaching an accuracy of 90,1%. It also offers anoverview of machine learning applications in e-commerce fraud detection, emphasizing the importance of algorithm selection, data preprocessing, and ethical data handling. It underscores the potential of these strategies in minimizing financial fraud, thereby contributing to the security and
trustworthiness of online transactions.
Referência:
ROCCO, Thiago; LEAL, Adriano Galindo. Machine learning in ecommerce fraud detection: a systematic literature review and comparative analysis of advanced techniques. In: INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND TECHONLOGY MANAGEMENT VIRTUAL, 20., 2024, São Paulo. Proceedings… 31 p. [on-line]
ROCCO, Thiago; LEAL, Adriano Galindo. Machine learning in ecommerce fraud detection: a systematic literature review and comparative analysis of advanced techniques. In: INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS AND TECHONLOGY MANAGEMENT VIRTUAL, 20., 2024, São Paulo. Lecture and Abstract…
Acesso ao trabalho no site do Evento:
https://www.tecsi.org/contecsi/index.php/contecsi/20thCONTECSI/paper/view/7305/4830