A study of educational evaluation models and their legal compliance based on big data analytics models

Teaching evaluation is the feedback on the teaching effect of teachers and the learning effect of students. It has become a critical link in colleges and universities teaching management and teaching inspection. This paper proposes and applies an improved BT-SVM multi-classification algorithm to the education evaluation model. By calculating the relative distance between classes, the error accumulation phenomenon existing in the traditional SVM when dealing with multi-classification problems is solved. A classifier structure based on an incomplete binary tree is constructed to automatically classify teaching data by gradually dividing the data set and training the SVM classifier. By calculating the decision function value of the test sample in the binary tree, the category to which it belongs can be quickly determined. The education evaluation model follows the principle of legal compliance to improve the quality and efficiency of model evaluation and ensure the rule of law construction in colleges and universities. The research results show that the error rate of the BT-SVM algorithm in machine learning is below 0.1%, the fairness index is between 0.1-2, and the prediction accuracy is 96%. It shows that the machine learning algorithm can effectively improve the efficiency of education evaluation work and has the principle of fair legal compliance.