Population prediction method based on LS-SVM-Leslie combination model

• Main Authors: CHEN SENBO, CAO JINXIN, WANG HAOCHEN, CHEN XIANG, JU XIAOLIN, SHEN YIHENG, ZHAI JUANNA
• Format: Patent
• Language: Chinese; English
• Published: 13.12.2022
• 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; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a population prediction method based on an LS-SVM-Leslie combined model, and belongs to mathematics and computer science. The problem that a traditional population prediction model lacks a gender proportion, an age structure and a population data change rule is solved. According to the technical scheme, the method comprises the following steps that S1, data are collected and preprocessed; s2, selecting a prediction index and estimating a birth ratio; s3, predicting a growth rate D1 of a specific age and a male/female death rate D2 by using an LS-SVM model; s4, inputting the D1 and the D2 into a Leslie model, and outputting specific initial age data D3; s5, taking D3 as an input parameter of Leslie in the next year, and iteratively outputting population data of each year; s6, establishing a time sequence prediction model and a gray system prediction model; and S7, combining the two models in the step S6 based on the weight, and outputting a prediction result. The population prediction me