A Multiperspective Fraud Detection Method for Multiparticipant E-Commerce Transactions

Abstract

Detection and prevention of fraudulent transactions in e-commerce platforms have always been the focus of transaction security systems. However, due to the concealment of e-commerce, it is not easy to capture attackers solely based on the historic order information. Many researches try to develop technologies to prevent the frauds, which have not considered the dynamic behaviors of users from multiple perspectives. This leads to an inefficient detection of fraudulent behaviors. To this end, this paper proposes a novel fraud detection method that integrates machine-learning and process mining models to monitor real-time user behaviors. First, we establish a process model concerning the B2C e-commerce platform, by incorporating the detection of user behaviors. Second, a method for analyzing abnormalities that can extract important features from event logs is presented. Then, we feed the extracted features to a Support Vector Machine (SVM) based classification model that can detect fraud behaviors. We demonstrate the effectiveness of our method in capturing dynamic fraudulent behaviors in e-commerce systems through the experiments.

Modeling and Analyzing Logic Vulnerabilities of E-Commerce Systems at the Design Phase

“…However, for enhancing efficiency and usability of the distributed business interaction process, some messages are not signed in the checkout process, which cannot be regarded as a security weakness, as the merchant directly verifies the data integrity with the TPP. This interactive mechanism guarantees the security in many real cases [1], [2], [6], [7], [13]. In the above discussed scenario, the two calls sent to TPP ensure the data consistency among the merchant and TPP.…”

“…E -COMMERCE with multi-participants has rapidly evolved worldwide, and becomes increasingly popular in the global economy. The prevalence of online network and smart mobile devices contribute significantly to the rise of e-commerce [1], [2]. E-commerce systems characterize extreme design complexities, such that the dynamism of business interactions among heterogeneous participants imposes an increased level of practical challenges in implementing a perfectly secure checkout process.…”

“…Many web stores today often utilize web Application Programming Interfaces (APIs) of TPPs such as Google Checkout, AliPay and PayPal for enabling their cashier services. As a result, today's ecommerce businesses have become increasingly hybrid, with their program logic being distributed across multi-participants, including the servers and their clients, along with various third party API service providers [2], [3].…”

A New Framework for Fraud Detection in Bitcoin Transactions Through Ensemble Stacking Model in Smart Cities

“…In [26], the proposed method used a multiperspective approach that considered various perspectives of the cryptocurrency transaction, including the transaction amount, payment method, shipping method, and user behavior. The authors used ML algorithms, including DT and SVM, to identify potentially fraudulent transactions based on the features extracted from the various transaction perspectives.…”

“…Proposed SINN-RD [24] Accuracy, Recall and Precision Existing techniques do not tackle Blackbox issue Used LR, KNN, RF, and NN [25] ROC, F1score, Specificity and Recall Existing techniques are not efficient for handling big data Used SVM [26] Precision, Recall, F1-score and AUC Binary classification issue in cryptocurrency Used ML techniques (LR, KNN, NB, RF and XGBoost) [27] Accuracy, F1-score, Precision and Recall Limited accuracy and performance of individual classifiers Used SNN and optimizeable DT [29] Precision, Recall, F1-score, and AUC. Existing research do not concentrate on fraud detection Used RF and XGBoost [30] Accuracy, F1-score and AUC-ROC curve Issue in Virtual Private Network (VPN) tunneling Used SVM, KNN, NB and RF [32] MSE, TP and FP illicit activities in [31].…”