Abstract：Recent research on the assessment of college teachers' promotions has predominantly focused on qualitative approaches, offering suggestions to enhance fairness, objectivity and efficiency within promotion systems. Addressing this gap, this study proposes a method to predict promotion outcomes based on teachers' characteristics, including teaching and research abilities. This article integrates qualitative and quantitative analyses to evaluate promotion criteria and find factors affecting teachers' promotion. The promotion results are correlated with the application characteristics, confirming their statistical significance through hypothesis testing. Additionally, the quantitative analysis reduces subjective bias based on visual data and statistical methods. Machine learning methods are applied to teacher promotion prediction. Results categorizing promotion outcomes are refined using Logistic regression, K-nearest neighbor, and BP neural network models, with the BP neural network showing superior performance. Furthermore, an optimized BP neural network using principal component analysis demonstrates improved metrics. This study contributes a precise method to predict college teachers’ promotion outcomes, offering insights to refine faculty evaluation systems.

Keywords：College teacher, machine learning, promotion evaluation, quantitative analysis

基金资助：This work was supported in part by the National Social Science Fund of China under Grant 21&ZD163, in part by the National Natural Science Foundation of China under Grant 62472203, in part by the Fundamental Research Funds for the Central Universities under Grant lzujbky-2023-16, and in part by the Supercomputing Center of Lanzhou University.

原文链接：https://ieeexplore.ieee.org/abstract/document/10753013