Research on Human Resource Multi-source Data of Electric Power Enterprises Based on XGBoost Modeling

With the development of electric power enterprises, the importance of human resource data management is becoming more and more prominent. This paper proposes an employee satisfaction prediction model for electric power enterprises based on the XGBoost algorithm, Firstly, the human resource dataset provided by an electric power enterprise is used as the object for preprocessing, then the employee satisfaction prediction model is established based on the XGBoost algorithm, finally, model of this paper is compared and analyzed with other algorithmic models by taking the accuracy rate, the Fl value, and the AUC value as the evaluation indexes. The simulation results show that the corporate environment and personal performance have the greatest influence on employee satisfaction, and the prediction accuracy of this model is more advantageous than that of logistic regression LR and GBoost models.