An efficient credit card fraud detection approach using cost‐sensitive weak learner with imbalanced dataset

Abstract

AbstractThe usage of credit cards is increasing in the digitization era to purchase goods online or offline, and the number of fraudulent credit card transactions has also increased. Fraudulent transaction detection is a big issue in the credit card domain because the data set is highly imbalanced. The performance of traditional classification techniques has decreased due to this issue. Therefore, a dynamic fraud detection system is required to overcome this issue. This article proposes an efficient cost‐sensitive weak learner approach with a bagging and random forest classifier (CSWLB) to minimize misclassification problems and overcome the class imbalance issue. The proposed CSWLB approach is included in an adaptive algorithmic method (cost‐sensitive) with two weak learner ensembles (bagging‐random forest), which assigns high weight to the fraudulent transactions using the cost‐sensitive learning classifier and generates weight bags using a bagging ensemble classifier. Therefore, the random forest classifier has been implemented on the weight bags to improve classification accuracy. The proposed approach's effectiveness and efficiency have been computed on the Brazilian credit card data set. Its results have been compared with sampling, cost‐sensitive, and machine learning techniques. The proposed CSWLB approach obtained 765 total costs and 97.361% accuracy. The experimental results show that the proposed approach has outperformed compared to other techniques.