A Machine Learning Model for Product Fraud Detection Based On SVM

With the rise of IoT technology, more and more companies use this technology for daily work production. This technology will generate large amounts of data during the application process. If data can be used wisely, it will help companies make better decisions. It is very meaningful to establish a model based on supply chain data to determine whether there is fraud in the product transaction process. It can help merchants in the supply chain avoid fraud, default and credit risk, and improve market order. In this paper, we propose a fraud prediction model based on the SVM classification model. Due to the large amount of data provided by the materials, we first perform feature engineering on the data to obtain processed data that can be used for modeling, and then use the SVM classification model algorithm for data classification and regression. Experiments show that the accuracy of the SVM classification model is 98.61. Compared with logistic regression model and naive Bayes model, it has better data classification and regression capabilities.