摘要
根据凯里市乡村振兴局提供的2021年脱贫户帮扶台账数据,建立风险度量的统计模型.首先,使用混料多项式模型构建年收入预测模型;其次,使用logistics回归模型建立返贫风险预测模型,并结合SVM等机器学习算法得到“三类户”的线性分类模型;然后,通过评价得分数据构建与年人均年收入的非参数回归模型.通过多重模型的分析,为基层开展返贫风险排查工作提供技术辅助参考.
According to the 2021 poverty alleviation account data provided by Kaili Rural Revitalization Bureau,a statistical model for risk measurement is established.First,the mixed polynomial model is used to build the annual income prediction model.Secondly,the logistics regression model is used to build the poverty risk prediction model,and the linear classification model of"three categories of households"is obtained by combining SVM and other machine learning algorithms.Then,the non parametric regression model with the annual per capita annual income is built through the evaluation score data.Through the analysis of multiple models,it provides technical assistance for grass-roots units to carry out poverty alleviation risk screening.
作者
李光辉
姜泽琴
冯姝
LI Guanghui;JIANG Zeqin;FENG Shu(Kaili Universit y,Kaili,Guizhou,556011,China;Kaili Statistics Bureau,Kaili,Guizhou,556001,China)
出处
《凯里学院学报》
2024年第3期81-92,共12页
Journal of Kaili University
基金
国家自然科学基金青年项目(11901260)
贵州省科学技术基金(黔科合基础[2020]1Y010)
凯里学院博士专项课题(BS201807)。
