Commodity Price Analysis and Prediction Based on Ensemble Learning

Abstract

From the development of human social productive forces to a certain stage, commodities appear. Especially in modern society, people often need to buy things. When you buy something, there is a price issue. In order to help people grasp the price of a commodity, this paper proposes a commodity price analysis and prediction method based on ensemble learning. This method first obtains the historical data of the product; then simply analyzes the batch of data; then visualizes the data features; then adopts bagging regression in ensemble learning, using different weak classifiers (decision tree, support vector machine, K nearest neighbors), random forest, linear) for modeling comparison and analysis, the highest model accuracy rate can reach 0.9502; finally, five models are used to predict future prices. After testing, this method can be used in certain scenarios.