Price data trend prediction method and system based on neural network

• Main Authors: CHEN WEI, HE XUZHONG, ZHUANG XIAOYANG, SHI LEI, KE CHUCHANG, LI WENJUN
• Format: Patent
• Language: Chinese; English
• Published: 11.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a price data trend prediction method and system based on a neural network, and the method comprises the steps: obtaining the price of a chemical, a price impact factor, and the proportion of the price impact factor, building a database, dividing the data of the database into a training set and a test set, inputting the training set into a neural network model for training, and carrying out the prediction of the price data trend. According to the method, the initial price data trend prediction model is obtained, the effect of accurately predicting the price data trend of the chemical product can be effectively achieved, the initial price data trend prediction model is input through the test set for testing, and the price data trend prediction value of the chemical product is obtained; solving a relative error matrix of the price data trend prediction value and the true value of the chemical product to obtain a maximum value of the relative error matrix, performing judgment according to