Predicting teacher turnover in private universities: a machine learning approach based on 10 years of data and satisfaction factors

TL;DR

This paper uses 10 years of data and machine learning to predict teacher turnover in Chinese private universities, finding that job satisfaction factors like compensation and development are key.

Contribution

The study introduces an 'EFA + ML' hybrid approach to improve feature interpretability and prediction accuracy in teacher turnover prediction.

Findings

The KNN model achieved the highest predictive performance with 83.64% accuracy and 0.901 AUC.

The 'Compensation, Benefits, and Development' dimension explained 25.41% of the variance in turnover.

A hybrid approach combining EFA and ML enhances both interpretability and prediction robustness.

Abstract

Teacher turnover poses a significant challenge to the sustainable development of private universities in China. While machine learning (ML) has been increasingly applied to turnover prediction, existing studies often overlook psychological factors and lack longitudinal analysis.

This study integrates a 10-year longitudinal dataset with satisfaction surveys from a private university in Western China. Exploratory Factor Analysis (EFA) was employed to extract key dimensions influencing turnover. Three ML models—K-Nearest Neighbors (KNN), Naive Bayes (NB), and Backpropagation Neural Network (BPNN)—were constructed and evaluated using accuracy, F1-score, and AUC.

The KNN model achieved the highest predictive performance (accuracy = 83.64%, F1 = 84.16%, AUC = 0.901). The “Compensation, Benefits, and Development” dimension was identified as the most influential factor, accounting for 25.41% of the variance.

This study proposes an “EFA + ML” hybrid approach that enhances feature interpretability and prediction robustness, offering practical insights for human resource management in private higher education institutions.

Figures