sis 18: e46

Research Article

A credible predictive model for employment of college graduates based on LightGBM

Download379 downloads
  • @ARTICLE{10.4108/eai.17-2-2022.173456,
        author={Yangzi He and Jiawen Zhu and Weina Fu},
        title={A credible predictive model for employment of college graduates based on LightGBM},
        journal={EAI Endorsed Transactions on Scalable Information Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SIS},
        year={2022},
        month={2},
        keywords={employment rate of college students, predict model classification, characteristics prediction Accuracy},
        doi={10.4108/eai.17-2-2022.173456}
    }
    
  • Yangzi He
    Jiawen Zhu
    Weina Fu
    Year: 2022
    A credible predictive model for employment of college graduates based on LightGBM
    SIS
    EAI
    DOI: 10.4108/eai.17-2-2022.173456
Yangzi He1, Jiawen Zhu2, Weina Fu1,3,*
  • 1: College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, Hunan Province, China
  • 2: School of Education and Science, Hunan Normal University, Changsha, 410081, Hunan Province, China
  • 3: Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Hunan Normal University, Changsha, 410081, Hunan Province, China
*Contact email: fuwn@hunnu.edu.cn

Abstract

INTRODUCTION: "Improving the employment rate of college students" directly affects the stability of the country and society and the healthy development of the industry market. The traditional graduate employment rate model only predicts the future employment rate based on changes in historical employment data in previous years.

OBJECTIVES: Quantify the employment factors and solve the employment problems in colleges and universities in a targeted manner.

METHODS: We construct a credible employment prediction model for college graduates based on LightGBM.

RESULTS: We use the model to predict the employment status of students and obtain the special importance which is important to employment of college students.

CONCLUSION: The final result shows that our Model performs well in the two indicators of accuracy and model quality.