Research on the Path to Improve the Employment Quality of Private College Students under the Background of Big Data

Abstract

Abstract In this paper, we use space-sensitive crawler technology to obtain the initial data of college students’ employment quality research from the websites or databases of private colleges and universities. We determine the evaluation indexes of college students’ employment quality through data cleaning and conversion of the initial data. On this basis, because of the limitations of the clustering algorithm, grey correlation analysis is used to optimize the clustering algorithm, and the evaluation model of college students’ employment quality based on grey correlation optimization clustering is constructed. Then the clustering analysis of college students’ employment evaluation indexes is carried out. The results show that the main influencing factors of job satisfaction of female graduates in some disciplines such as literature, history and philosophy and education and law are family economic situation Q7 (-1.9328), participation in innovative and entrepreneurial activities Q8 (29.2178), political outlook Q11 (3.0279), and graduation destination Q13 (2.5824), and that this paper’s method is effective in revealing the key factors. This study benefits the enrichment and innovation of the research content of employment quality. It provides theoretical support for solving the problem of future employment quality of college students in private colleges and universities.