基于可解释机器学习的科技人才流动宏观影响因素研究

徐倪妮 ,  孟涵 ,  朱淑婉

南京师大学报(自然科学版) ›› 2026, Vol. 49 ›› Issue (3) : 127 -136.

PDF (2183KB)
南京师大学报(自然科学版) ›› 2026, Vol. 49 ›› Issue (3) : 127 -136. DOI: 10.3969/j.issn.1001-4616.2026.03.014

基于可解释机器学习的科技人才流动宏观影响因素研究

作者信息 +

Research on Macro-Level Factors Influencing Science and Technology Talent Mobility Using Explainable Machine Learning

Author information +
文章历史 +
PDF (2235K)

摘要

为精准识别影响科技人才流动的重要因素及其作用方式,利用 1978—2023 年中国 31 个省(直辖市、自治区)的面板数据,构建基于 XGBoost 的科技人才流动预测模型,并引入 SHAP 可解释性方法完成特征影响全局解释、特征依赖分析、特征交互分析及分区域解释。结果表明,科技人才流动受科研环境影响最为显著,其次为教育环境、经济发展水平、收入水平和生活便利度,产业结构的影响则相对较弱;科研环境与科技人才流动呈现正向线性关联,而其余因素则表现出复杂非线性关系;经济发展水平与科研环境、科研环境与生活便利度之间存在显著协同效应;东部、中部、西部及东北地区的科技人才流动的主导因素存在显著区域差异。据此,提出促进区域科技人才合理流动的政策建议。

Abstract

To accurately identify key influencing factors and their impact mechanisms on science and technology talent mobility, this study employed panel data of China's 31 provinces (municipality, autonomous region) from 1978 to 2023 to construct an XGBoost-based prediction model for science and technology talent mobility. The SHAP interpretation method was then introduced to conduct global interpretation of feature importance, feature dependency analysis, feature interaction analysis, and regional interpretation. The results indicate that: science and technology talent mobility is most significantly influenced by the research environment, followed by the education environment, economic development level, income level, and living convenience, while the impact of industrial structure is relatively weak; The research environment exhibits a positive linear relationship with science and technology talent mobility, whereas other factors demonstrate complex nonlinear relationships; Significant synergistic effects exist between economic development level and research environment, as well as between research environment and living convenience; Significant regional variations exist in the dominant drivers of talent mobility across eastern, central, western, and northeastern China. Based on these findings, policy recommendations are proposed to promote the rational mobility of science and technology talents among regions.

关键词

可解释机器学习 / 科技人才 / 人才流动 / 影响因素

Key words

explainable machine learning / science and technology talents / talent mobility / influence factor

引用本文

引用格式 ▾
徐倪妮,孟涵,朱淑婉. 基于可解释机器学习的科技人才流动宏观影响因素研究[J]. 南京师大学报(自然科学版), 2026, 49(3): 127-136 DOI:10.3969/j.issn.1001-4616.2026.03.014

登录浏览全文

4963

注册一个新账户 忘记密码

参考文献

[1]

黄海刚,曲越. 孔雀东南飞:经济转型与精英科学家流动[J].华中科技大学学报(社会科学版),2019,33(3):63-72.

[2]

柳瑛,苏丽锋,史薇. 中国科技领军人才流动的影响要素研究[J].技术经济,2025,44(4):25-35.

[3]

Zha Q. What factors influence the direction of global brain circulation: the case of Chinese Canada Research Chairholders[J].Compare: A Journal of Comparative and International Education, 2016, 46(2): 214-234.

[4]

YUE M, LI R, OU G, et al. An exploration on the mobility of leading research talents in China: from the perspective of distinguished young scholars[J].Scientometrics, 2020, 125(2): 1559-1574.

[5]

郭俊华,徐倪妮. 高新技术企业科技人才流动影响因素研究:以上海市为例[J].数量经济研究,2020,11(4):90-104.

[6]

徐娟,王建平. 中国大学高层次青年人才流动的影响因素:基于 5 类项目人才履历追踪的实证研究[J].现代大学教育,2021,37(3):78-87.

[7]

朱英,郑晓齐,章琰. 中国科技创新人才的流动规律分析:基于国家“万人计划”科技创新领军人才的实证研究[J].中国科技论坛,2020(3):166-173.

[8]

刘杨,有书涵,周建中. 我国科技智库人才流动特征及影响因素定量研究[J].科学学研究,2025,43(8):1588-1599.

[9]

王腾,关忠诚,郑海军,等. 全球顶尖科技人才流动的影响因素探析:基于扎根理论的分析[J].科学学研究,2024,42(7):1376-1386.

[10]

王冲. 基于灰色关联分析的高校科技人才流动影响因素及策略分析:以吉林省高校为例[J].情报科学,2019,37(5):47-52.

[11]

柳美君,李伟平,杨斯杰,等. 长三角区域一体化政策对科技人才流动的影响研究[J].科学学研究,2024,42(4):733—745+862.

[12]

王焘,马亚雪,吴柯烨. 区域新兴产业创新生态系统联动效应对科技人才流动影响研究[J].现代情报,2024,44(11):139-151.

[13]

陈茜,马向平,贾承丰,等. 基于决策树 ID3 算法的人才留汉吸引政策研究[J].武汉理工大学学报(信息与管理工程版),2019,41(2):148-153.

[14]

Al—Quhfa H, Mothana A, Aljbri A, et al. Enhancing talent recruitment in business intelligence systems: a comparative analysis of machine learning models[J].Analytics(basel), 2024, 3(3), 297-317.

[15]

Gazı MS, Nasiruddin M, Dutta S, et al. Employee attrition prediction in the USA: a machine learning approach for HR analytics and talent retention strategies[J].Journal of Business & Management Studies, 2024, 6(3), 47-59.

[16]

Chen T, Guestrin C. Xgboost: a scalable tree boosting system[C]//Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining. New York, USA, 2016: 785-794.

[17]

Lundberg SM, Lee SI. A unified approach to interpreting model predictions[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. New York, USA, 2017: 4768-4777.

[18]

李婧,产海兰. 空间相关视角下 R&D 人员流动对区域创新绩效的影响[J].管理学报,2018,15(3):399-409.

[19]

刘诗昆,姚奕. 城市科技人才流动水平的测算及其对绿色全要素生产率的影响研究:基于空间回归模型[J].南京师大学报(自然科学版),2025,48(2):1-9.

[20]

窦旺胜,秦波,郝美竹,等. 中国青年流动人口城市选择的空间特征及影响因素[J].地理研究,2023,42(5):1234-1247.

[21]

徐倪妮,郭俊华. 科技人才流动的宏观影响因素研究[J].科学学研究,2019,37(3):414-421,461.

[22]

齐宏纲,产健,师俊杰,等. 中国境外高水平科技人才回流的空间格局及影响因素[J].热带地理,2025,45(2):223-237.

基金资助

安徽省哲学社会科学规划青年资助项目(AHSKYQ2023D014)

AI Summary AI Mindmap
PDF (2183KB)

0

访问

0

被引

详细

导航
相关文章

AI思维导图

/

〈 〉