Application of Machine Learning in the Evaluation Model of Scientific Research Performance of Teachers

Abstract

Due to the small number of scientific research evaluation indicators of college teachers, the mathematical model of evaluation is uncertain and the subjective process of the evaluation process is too strong, this paper proposes a model of university teachers’ scientific research performance evaluation based on machine learning. The evaluation model uses the neighborhood rough set to reduce the index of the evaluation index and form the decision table as the input data of the support vector machine algorithm, which reduces the dimension of the sample data and improves the training speed of the evaluation model. The particle swarm optimization algorithm is used to optimize the parameter search of the support vector machine algorithm, which improves the prediction accuracy of the evaluation model. Finally, the feasibility and practicability of the scientific research performance evaluation model based on machine learning are proved through experiments.