A Model to Detect the Fraud of Electronic Payment Card Transactions Based on Stream Processing in Big Data

With the growing use of electronic cash cards, the number of transactions with these cards has also increased rapidly, so the importance of using fraud detection models has been paid attention to by financial organizations from various aspects. Electronic cash card fraud detection models often on a single algorithm, optimization of classifications and clusters, to find fraudulent patterns, which provide unsupervised or supervised methods. But the proposed model will use both unsupervised and supervised methods to detect fraud so that it will take advantage of the advantages of both methods. In the proposed method, by selecting the most important features of users’ behavioral patterns such as transaction time and values, their behavioral modeling is done which includes extracting different profiles of users and determining threshold values for each profile. The proposed model will work in real-time by combining two filters to detect electronic card fraud. The first filter is a fast filter that includes a number of unsupervised algorithms, but the second filter is an explicit filter that consists of a number of supervised algorithms. The proposed model creates a profile of the cardholder and measures the degree of deviation of the cardholder’s behavior pattern in new transactions through the Map/Reduce approach for parallel execution alongside the human observer. After then the transaction has been completed and the maximum difference between two consecutive orders of observations, the fraud or non-fraud label will be applied to the transaction and added to the relevant database for future use, in order to detect the deviation of the transaction. According to the simulation results of the proposed model, the accuracy criterion with All Variables, reducing the dimensions of PCA and LASSO is 0.985, 0.987, and 0.980, respectively. F1-Score criterion with All Variables, PCA, and LASSO dimension reduction will be 0.681, 0.676, and 0.669 respectively. The simulation results show that the case with the highest F1 score is the classification of the Proposed Model using all variables. By comparing the simulation results, it can be seen that the F1 score has a high discriminating power between different classification algorithms because the values obtained from it are more different. Also, the results of the calculated performance change values of each pre-processed data with dimension reduction showed that PCA and All variables have very similar performance.