Predictive modeling study demonstrates high accuracy in identifying sales fraud on Facebook Marketplace, suggesting Naïve Bayes can enhance transaction security.
The rapid development of digital shopping media is accompanied by increasing cases of online fraud, especially through social media platforms such as Facebook. This study aims to develop a prediction model for the risk of online sales fraud using the Naïve Bayes algorithm. The data used is the data of buying and selling transactions that occur through the Facebook marketplace. The data has been collected on the Kaggle platform so that it can be used directly. Data in the form of extracted features include seller characteristics, products sold, number of transactions, device usage and other fraud indicators. Important features that affect the potential for fraud are identified and used in the machine learning process. The results of the study show that the Naïve Bayes model is able to provide accurate predictions in identifying the risk of online sales fraud, with a satisfactory accuracy rate of 95%. The results of the study are expected to contribute to the development of a more effective fraud detection system and increase user confidence in making online transactions.
No takes yet. Share an insight, caveat, or question.
Pasha et al. (2025) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: