基于Adaboost的长江经济带多维相对贫困测度与预警模型  

A Multi-dimensional Relative Poverty Measurement and Early Warning Model in the Yangtze River Economic Belt Based on Adaboost

作　　者：沈洁 SHEN Jie(School of Economics and Management,Hunan Institute of Science and Technology,Yueyang 414006,China)

机构地区：[1]湖南理工学院经济与管理学院,湖南岳阳414006

出　　处：《湖南理工学院学报（自然科学版）》2024年第4期66-72,共7页Journal of Hunan Institute of Science and Technology(Natural Sciences)

基　　金：湖南省教育厅科学研究项目(22C0356)。

摘　　要：确保不发生规模性返贫是解决相对贫困问题的一个重要方面,而精确识别相对贫困群体是实现长效治理贫困的前提条件.基于2020年中国家庭追踪调查数据库,构建多维贫困指标体系,运用A-F双界限法对长江经济带区域11个省市的家庭相对贫困情况进行测度,为每个家庭添加贫困与否的标签,运用Adaboost算法建立长江经济带区域的相对贫困家庭预警模型.结果显示,该模型的预测准确率、召回率、精确率、F1值分别达到城镇数据的99.66%、100.00%、99.43%、99.71%和农村数据的99.09%、100.00%、97.73%、98.8%.对各特征变量的重要程度进行分析,发现教育、借款被拒、医疗健康、收入、家庭资产等方面对家庭相对贫困的影响更大.Ensuring that there is no large-scale return to poverty is an important aspect of relative poverty.And accurately identifying relative poverty groups is a prerequisite for achieving long-term poverty governance.This article constructs a multidimensional poverty indicator system based on the 2020 China Family Panel Studies database.The A-F double boundary method is used to measure the relative poverty situation of households in 11 provinces and cities in the Yangtze River Economic Belt region.And a poverty label is added to each household.The Adaboost algorithm is used to establish a relative poverty household identification model in the Yangtze River Economic Belt region.The results show that the accuracy,recall,precision,and F1 score of the model for predicting relative poverty reached 99.66%,100.00%,99.43%and 99.71%of urban data and 99.09%,100.00%,97.73%and 98.8%of rural data.Respectively,it demonstrates the good generalization ability of the model.By analyzing the importance of each characteristic variable,it was found that education,loan rejection,healthcare,income,and household assets have a greater impact on relative poverty in households.

关 键 词：长江经济带 相对贫困预警 ADABOOST A-F法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]