文献类型：期刊文献

英文题名：Design of performance assessment and management model for regional technological innovation under the background of machine learning

作者：Zhang, Wenjing[1];Zhang, Hanyuan[2];Tian, Kang[3];Zhang, Huaping[1]

第一作者：Zhang, Wenjing

通讯作者：Tian, K[1]

机构：[1]North China Univ Water Resources & Elect Power, Sch Management & Econ, Zhengzhou 450046, Henan, Peoples R China;[2]Henan Univ Econ & Law, Sch Engn Management & Real Estate, Zhengzhou 450046, Henan, Peoples R China;[3]Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou 450046, Henan, Peoples R China

第一机构：North China Univ Water Resources & Elect Power, Sch Management & Econ, Zhengzhou 450046, Henan, Peoples R China

通讯机构：[1]corresponding author), Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou 450046, Henan, Peoples R China.

年份：2024

卷号：28

期号：2

外文期刊名：INTERNATIONAL JOURNAL OF DATA MINING AND BIOINFORMATICS

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001197473000007)】；

基金：This work was supported by the Academic Degrees and Graduate Education Reform Project of Henan Province, 'Research and practice on the construction mode and effectiveness evaluation of new liberal arts off-campus practice education bases in colleges and universities with industry characteristics', the project number is 2021SJGLX013Y. And supported by the Higher Education Reform and Practice Project of Henan Province, 'Reform and practice of training mode for postgraduates of business administration subject facing the high-quality development of water conservancy in the new stage', the project number is 2021SJGLX159.

语种：英文

外文关键词：performance evaluation management; management mode; random forest; decision tree; machine learning

摘要：This study addresses the limitations and primitiveness of performance evaluation management in regional technological innovation enterprises. We propose a methodology based on the random forest algorithm to overcome these issues. The methodology involves preprocessing raw data from a technology company's project management system through data cleaning, feature selection, and feature transformation. Using the ID3 algorithm, we construct an index weight evaluation model by recursively creating a decision tree and selecting features based on information gain criteria. The refined model generates a performance evaluation total score. Experimental results demonstrate that the random forest algorithm achieves a satisfactory assessment of regional technological innovation performance, with a testing accuracy of 94.20%. These findings establish a scientific foundation for performance evaluation management, enabling enterprises to enhance accuracy and efficiency.