Supply Fraud Forecasting using Decision Tree Algorithm

Abstract

In recent years, the Internet of Things (IoT) has been developing rapidly as an emerging technology, and more and more companies have begun to adopt this technology, which has led to an exponential increase in the amount of data. If data is used correctly, it will be very helpful for companies to discover hidden patterns. In order to make better decisions in the future, the use of machine learning algorithms to predict the sales of products and commodities has become a hot spot for researchers and companies. In this article, we use a product fraud detection model based on the decision tree, which combines algorithm and feature engineering processing to predict the sales problem of a certain product. We evaluate the prediction model based on the specific information of DataGo’s supply chain data set. The experimental results show that our evaluation method based on decision tree has a good evaluation effect. Our Accuracy index is higher than Logistic algorithm and SVM algorithm.