An Analysis of the Effectiveness of Machine Learning Theory in the Evaluation of Education and Teaching

Abstract

Artificial intelligence was first proposed in the 1950s, when it was only a forward-looking concept. If machines can have the same learning ability as human beings and the computing power of computers themselves, this concept has been placed high hopes. Until about 2010, with the explosion of data volume and the improvement of computer performance, machine learning has become a leader in breaking through the bottleneck of artificial intelligence. Research on machine learning in education and teaching has attracted much attention. From the above research status, we can see that in the current period of the vigorous development of machine learning, many applications are still not perfect and ordinary education and teaching evaluation is difficult to meet people’s requirements, so how to gradually improve its effectiveness is a significant goal with research significance and practical interests. However, in the environment of colleges and universities, prediction information and evaluation methods have important application value and development space in education and teaching. In this context, according to the theory of machine science, the effectiveness of several conventional prediction and evaluation methods is analyzed. In this paper, machine learning theory is used to study college students’ performance prediction and credit evaluation, as well as teaching quality evaluation and comprehensive ability evaluation in colleges and universities. Questionnaire survey is used to investigate and analyze the results. The effectiveness of machine theory in teaching is analyzed. It is found that machine learning has great advantages in education and teaching evaluation. It builds models in complex computing environment and is not affected by human factors; the effectiveness of prediction and evaluation is significant.