Explainable AI in Credit Card Fraud Detection: Interpretable Models and Transparent Decision-making for Enhanced Trust and Compliance in the USA

Abstract

Credit Card Fraud presents significant challenges across various domains, comprising, healthcare, insurance, finance, and e-commerce.  The principal objective of this research was to examine the efficacy of Machine Learning techniques in detecting credit card fraud. Four key Machine Learning techniques were employed, notably, Support Vector Machine, Logistic Regression, Random Forest, and Artificial Neural Network. Subsequently, model performance was evaluated using Precision, Recall, Accuracy, and F-measure metrics. While all models demonstrated high accuracy rates (99%), this was largely due to the dataset's size, with 284,807 attributes and only 492 fraudulent transactions. Nevertheless, accuracy solely did not provide a comprehensive comparison metric. Support Vector Machine showed the highest recall (89.5), correctly identifying the most positive instances, highlighting its efficacy in detecting true positives. On the other hand, the Artificial Neural Network model exhibited the highest precision (79.4, indicating its capability to make accurate identifications, making it proficient in optimistic predictions.