乡村农户贫困状态特征因子筛选与分析框架：兼论我国乡村振兴路径选择

doi:10.16381/j.cnki.issn1003-207x.2021.2648

中国管理科学 ›› 2022, Vol. 30 ›› Issue (12): 234-244.doi: 10.16381/j.cnki.issn1003-207x.2021.2648

• 论文 • 上一篇

乡村农户贫困状态特征因子筛选与分析框架：兼论我国乡村振兴路径选择

袁先智¹, ², ³, ⁴, ⁵, ⁶, 赵旻⁷, 刘海洋⁶, 周云鹏⁶, 严诚幸⁶, 石宝峰⁸, 柴娜娜⁸, 林健武², 何诚颖², 马胜¹, 张千友¹, 丁晓蔚⁹

1.成都大学商学院，四川成都610106； 2.三亚学院盛宝金融科技商学院，海南三亚572000；3.中山大学管理学院，广东广州510275； 4.重庆理工大学理学院，重庆400054；5.华东理工大学商学院，上海200237； 6.上海翰墨数字科技有限公司，上海200093；7.云南省烟草专卖局公司信息中心，云南昆明650000；8.西北农林科技大学经济管理学院，陕西咸阳712100；9.南京大学信息管理学和南大普惠三农金融科技创新研究中心，江苏南京210023

收稿日期:2021-04-20 修回日期:2022-01-14 发布日期:2023-01-10
通讯作者: 张千友(1979-)，男(汉族)，四川绵阳人，成都大学商学院，教授，博士，研究方向：农业经济管理，Email：zhangqianyou@163.com. E-mail:zhangqianyou@163.com
基金资助:
国家自然科学基金资助项目(71971031,U1811462,72173096,71873103)；国家社会科学基金资助项目(19BTQ070)

The Framework for Characteristic Factors of Poverty Statusby Using AI Algorithms:Related to the Path Choice of Rural Revitalization in China

YUAN George Xianzhi¹, ², ³, ⁴, ⁵, ⁶, ZHAO Min⁷, LIU Hai-yang⁶, ZHOU Yun-peng⁶, YAN Cheng-xing⁶, SHI Bao-feng⁸, CHAI Na-na⁸, LIN Jian-wu², HE Cheng-ying², MA Sheng¹, ZHANG Qian-you¹, DING Xiao-wei⁹

1. Business School, Chengdu University, Chengdu 610106;2. Saxo Fintech Business School, University of Sanya, Hainan, 572000;3. Business School, Sun Yatsen University, Guangdong 510275;4. School of Science, Chongqing University of Technology, Chongqing 400054;5. Business School, East China University of Science and Technology, Shanghai 200237;6. Shanghai Hammer Digital Technology, LtD.Hammer, Shanghai 200093;7. Information Center, Yunnan Tobacco Company, Kunming 650000;8. College of Economics and Management, Northwest A&F University, Xianyang 712100;9. School of Information Management & Inclusive & Rural Fintech Innovation Research Center, Nanjing University, Nanjing 220023, China

Received:2021-04-20 Revised:2022-01-14 Published:2023-01-10
Contact: 张千友 E-mail:zhangqianyou@163.com

摘要/Abstract

摘要： 本文构建了刻画乡村农户贫困状态的特征因子的提取算法和分析框架，旨在实现和帮助完善家庭农场的持续发展，尤其是由贫困农户组成或参与的家庭农场在发展需要的融资方面的乡村信用评估，推动有效地制订对应政策和落地方案，巩固脱贫攻坚成果和防止返贫。本文的最大亮点是以“分类与回归树”(CART)分析和“吉布斯抽样”(Gibbs Sampling)的人工智能算法为工具，对乡村农户贫困状态的特征因子提取建立了对应的框架和分析流程。基于国内某地区乡村建档立卡数据库的31,116个样本，实证研究筛选出12个刻画乡村农户贫困状态高度关联的特征因子，并进一步对特征因子的有效性进行了ROC曲线和AUC测试。结果表明以特征因子分析框架为基础，建设配套的乡村信用评估体系是支持乡村振兴的可持续性最佳解决途径之一，除了能够为乡村贫困户获得持续工作的基本技能或生产环境的改善提升上得到持续性的融资支持提供评估依据和数据支持，也能为乡村和城镇“传帮带”等生产和商务平台的建立提供可持续的基础性数据和信用分析的动态支持。

关键词: 机器学习；吉布斯抽样；家庭农场；信用评级；乡村振兴；贫困状态；关联特征

Abstract: The goal of this paper is to establish a framework and associated analysis process for the extraction of related features to depict the poverty status of rural farmers. Based on the 18 types of data covered by a rural filing cardin China, combined with CART analysis and Gibbs sampling algorithm, 12 highly related characteristic factors are screened out to describe the poverty status of rural households.

Key words: machine learning algorithm; gibbs sampling; family farm; credit rating; rural vitalization; poverty state; associated feature

中图分类号:

F320

袁先智, 赵旻, 刘海洋, 周云鹏, 严诚幸, 石宝峰, 柴娜娜, 林健武, 何诚颖, 马胜, 张千友, 丁晓蔚. 乡村农户贫困状态特征因子筛选与分析框架：兼论我国乡村振兴路径选择[J]. 中国管理科学, 2022, 30(12): 234-244.

YUAN George Xianzhi, , , , , , ZHAO Min, LIU Hai-yang, ZHOU Yun-peng, YAN Cheng-xing, SHI Bao-feng, CHAI Na-na, LIN Jian-wu, HE Cheng-ying, MA Sheng, ZHANG Qian-you, DING Xiao-wei. The Framework for Characteristic Factors of Poverty Statusby Using AI Algorithms:Related to the Path Choice of Rural Revitalization in China[J]. Chinese Journal of Management Science, 2022, 30(12): 234-244.

参考文献

［1］吴重庆.小农户视角下的常态化扶贫与实施乡村振兴战略的衔接［J］.马克思主义与现实,2020(3):8-15+195.Wu Chongqing. Integrating regularized poverty alleviation from the perspective of smallholder farmers and the implementation of the rural revitalization strategy［J］. Marxism & Reality, 2020(3): 8-15+195.
［2］中共中央国务院关于抓好“三农”领域重点工作确保如期实现全面小康的意见［J］.中华人民共和国国务院公报,2020(5):6-12.State department of the CPC central committee: Opinions on grasping the key work in the field of ‘agriculture, rural areas and farmers’ to ensure a comprehensive Well-off society on time［J］. Gazette of the State Council of the People’s Republic of China, 2020 (5): 6-12.
［3］中共中央国务院关于全面推进乡村振兴加快农业农村现代化的意见［J］.中华人民共和国国务院公报,2021(7):14-21.State department of the CPC central committee: Opinions on comprehensively promoting rural revitalization and accelerating agricultural and rural modernization［J］.Gazette of the State Council of the People’s Republic of China, 2021(7): 14-21.
［4］范和生,武政宇.相对贫困治理长效机制构建研究［J］.中国特色社会主义研究,2020(1):63-69. Fan Hesheng, Wu Zhengyu. On setting up long effective mechanism of eliminating relative poverty［J］. Studies on Socialism with Chinese Characteristics, 2020 (1): 63-69.
［5］魏后凯,杜志雄,苑鹏,于法稳,崔红志.中国农村发展报告(2020)-聚焦“十四五”时期中国的农村发展［M］.北京：中国社会科学出版社,2020.Wei Houkai, Du Zhixiong, Yuan Peng, et al. China rural development report (2020)-Focus on China’s rural development during the ‘14th Five-Year’ period［M］. Beijing: China Social Sciences Press, 2020.
［6］尹志超,郭沛瑶.精准扶贫政策效果评估—家庭消费视角下的实证研究［J］.管理世界,2021,37(4):64-83. Yin Zhichao, Guo Peiyao. The impact of targeted poverty alleviation policy on consumption: Evidence from China household finance survey［J］. Management World, 2021, 37(4): 64-83.
［7］汪三贵,孙俊娜.全面建成小康社会后中国的相对贫困标准、测量与瞄准—基于2018年中国住户调查数据的分析［J］.中国农村经济,2021(3):2-23.Wang Sangui, Sun Junna.China’s relative poverty standards, measurement and targeting after the completion of building a moderately prosperous society in an All-round way: An analysis based on data from China urban and rural household survey in 2018［J］. Chinese Rural Economy, 2021(3): 2-23.
［8］郭君平,谭清香,曲颂.进城农民工家庭贫困的测量与分析—基于“收入-消费-多维”视角［J］.中国农村经济,2018(9):94-109.Guo Junping, Tan Qingxiang, Qu Song. The poverty of rural migrant families: An analytical framework from the perspectives of income, consumption and Multi-dimensions［J］. Chinese Rural Economy, 2018(9): 94-109.
［9］林万龙,陈蔡春子.从满足基本生活需求视角看新时期我国农村扶贫标准［J］.西北师大学报(社会科学版),2020,57(2):122-129.Lin Wanlong, Chen Caichunzi. Measuring rural poverty standards in China in the new era from the perspective of satisfying basic needs of life［J］. Journal of Northwest Normal University (Social Sciences), 2020, 57(2): 122-129.
［10］潘文轩,阎新奇.2020年后制定农村贫困新标准的前瞻性研究［J］.农业经济问题,2020(5):17-27.Pan Wenxuan, Yan Xinqi. A prospective study on the new rural poverty standard after year 2020［J］. Issues In Agricultural Economy, 2020(5): 17-27.
［11］王小林,冯贺霞.2020年后中国多维相对贫困标准：国际经验与政策取向［J］.中国农村经济,2020(3):2-21. Wang Xiaolin, Feng Hexia. China’s multidimensional relative poverty standards in the Post-2020 era: international experience and policyorientation［J］. Chinese Rural Economy, 2020(3): 2-21.
［12］周力.相对贫困标准划定的国际经验与启示［J］.人民论坛·学术前沿,2020(14):70-79.Zhou Li. International experience and insight of relative poverty standard［J］. RenmingLuntan·XueshuQianyan, 2020(14): 70-79.
［13］田甜,李博,左停.“懒惰的穷人”的产生:一种贫困发生的新型解释框架—基于贵州省黔西南州林村实地调研的思考［J］.农村经济,2021(2):37-47.Tian Tian, Li Bo, Zuo Ting. The emergence of “lazy poor”: a new explanatory framework for poverty occurrence - based on the field research in Lincun Village, southwestern Guizhou Province［J］. Rural Economy, 2021(2): 37-47.
［14］胡俊波,熊若希,唐张雨青.“信用评价”能缓解农村小微企业“融资难”吗?［J］.农村经济,2021(2):77-86.Hu Junbo, Xiong Ruoxi, Tang Zhangyuqing. Can credit evaluation alleviate the financing difficulty of rural small and micro enterprises［J］. Rural Economy, 2021(2): 77-86.
［15］冯子纯,李凯杰.“政银企+N”资产收益扶贫模式运行分析—以牧原生猪养殖产业链为例［J］.农村经济,2021(2):68-76.Feng Zichun, Li Kaijie.Analysis on the operation of ‘government bank enterprise+N’ asset income poverty alleviation model-takingMuyuan pig breeding industry chain as an example［J］. Rural Economy, 2021(2): 68-76.
［16］ Alkire S, Santos M E. Measuring acute poverty in the developing world: Robustness and scope of the multidimensional poverty index［J］. World Development, 2014, 59: 251-274.
［17］ Friedman J H, Olshen R A, Stone C J. Classification and regression trees［M］. Brooks/Cole Publishing, Monterey, 1984.
［18］ Loh W Y. Classification and regression trees［J］. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2011,1(1): 14-23.
［19］袁先智,刘海洋,周云鹏,等.基金关联特征提取的大数据随机搜索算法及应用［J］.管理科学,2020,33(6):41-53.Yuan Xianzhi, Liu Haiyang, Zhou Yunpeng, et al. Extraction of features related for funds by using big data stochastic search algorithms and applications［J］. Management World, 2020, 33(6): 41-53.
［20］袁先智,狄岚,李祥林,等.在大数据框架下基于吉布斯抽样的随机搜索方法在金融风险特征提取中的应用［J］.计量经济学报,2021,1(2):377-408.Yuan Xianzhi, Di Lan, Li Xianglin, et al. The framework for the extraction of risk factors by using stochastic search method based on gibbs sampling algorithm in fintech［J］. China Journal of Econometrics, 2021, 1(2): 377-408.
［21］ Qian Guoqi, Field C. Using MCMC for logistic regression model selection involving large number of candidate models［J］. Monte Carlo and Quasi-Monte Carlo Methods 2000, 2002: 460-474.
［22］ Fawcett T. An introduction to ROC analysis［J］. Pattern Recognition Letters, 2006, 27(8): 861-874.
［23］ Hanley J A, McNeil B J. A method of comparing the areas under receiver operating characteristic curves derived from the same cases［J］. Radiology, 1983, 148(3): 839-843.
［24］ Macmillan N A, Creelman C D. Detection theory: A User’s guide (2nd editor)［M］.Mahwah, NJ: Lawrence Erlbaum Associates. ISBN, 2005.
［25］冯怡琳.中国城镇多维贫困状况与影响因素研究［J］.调研世界,2019 (3):3-10.Feng Yilin. Research on the status quo and factors of China’s urban Multi-dimensional poverty［J］. The World of Survey and Research, 2019(3): 3-10.
［26］李昊源,崔琪琪.农村居民家庭贫困的特征与原因研究--基于对甘肃省调研数据的分析［J］.上海经济研究,2015(4):79-86. Li Haoyuan, Cui Qiqi. Study on the poverty characteristics and reasons of rural Households-analysis based on the micro data of gansu province［J］. Shanghai Journal Of Economics, 2015(4): 79-86.
［27］ Bishop C M. Pattern recognition and machine learning［M］. New York: Springer, 2017.
［28］ Geman S, Geman D. Stochastic relaxation, gibbs distributions, and the bayesian restoration of images［J］. IEEE Trans. Pattern Anal. Mach.Intell, 1984, 6(6): 721-741.
［29］ Qian Guoqi, Rao C R, Sun Xiaoying, et al. Boosting association rule mining in large datasets via gibbs sampling［J］. Proceedings of the National Academy of Sciences, 2016, 113(18): 4958-4963.
［30］ Glasserman P. Monte carlo methods in financial engineering［M］. New York: Springer Science & Business Media, 2013.
［31］ Narisetty N N, Shen Juan, He Xuming. A consistent and scalable gibbs sampler for model selection［J］. Journal of the American Statistical Association, 2019, 114(527): 1205-1217.
［32］ Bai Cunguang, Shi Baofeng, Liu Feng, et al. Banking credit worthiness: Evaluating the complex relationships［J］. Omega, 2019, 83, 26-38.
［33］欧高炎,朱占星,董彬,等.数据科学引论［M］.北京：高等教育出版社, 2017. Ou Gaoyan, Zhu Zhanxing, Dong Bin, et al. Introduction to data science［M］. Beijing: Higher Education Press, 2017.
［34］ Agrawal R，Srikant R. Fast algorithms for mining association rules［C］∥Proceedings 20th International Conference Very Large Data Bases, Chile, Sep.12-15,1994.
［35］ Akaike H. A new look at the statistical model identification［J］. IEEE Transactions on Automatic Control, 1974, 19(6): 716-723.
［36］ Paz A, Moran S. Non-deterministic polynomial optimization problems and their approximations［J］. Theoretical Computer Science, 1981, 15(3): 251-277.
［37］杨莲,石宝峰.基于Focal Loss修正交叉熵损失函数的信用风险评价模型及实证［J/OL］.中国管理科学:1-12［2021-12-14］.https://doi.org/10.16381/j.cnki.issn1003-207x.2020.2188. Yang Lian, Shi Baofeng. Credit risk evaluation model and empirical research based on focal loss modified cross-entropy loss function［J/OL］.Chinese Journal of Management Science:1-12［2021-12-14］.https://doi.org/10.16381/j.cnki.issn1003-207x.2020.2188.

乡村农户贫困状态特征因子筛选与分析框架：兼论我国乡村振兴路径选择

The Framework for Characteristic Factors of Poverty Statusby Using AI Algorithms:Related to the Path Choice of Rural Revitalization in China

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

Metrics

本文评价

推荐阅读 0