Evaluation of Learning Effect of Reverse Teaching Design Based on BP Neural Network

Abstract

A BP neural network model is built for the comprehensive evaluation of students' learning effects of market research courses using Python. Combined with the reverse instructional design in market research courses, a learning effect evaluation index system with 13 indicators under the three dimensions of knowledge, ability, and quality goal achievement is constructed. By using 263 sets of sample data of simulation experiment learning training, students' learning effect in the market research course is evaluated based on BP neural network. The BP neural network-based evaluation model of the learning effect of the course avoids the subjectivity of evaluation index weight evaluation and improves the speed of evaluation. Compared with traditional weight evaluation, the proposed method has better efficiency and effect. The test result shows that the comprehensive evaluation model has strong applicability and provides new methods and ideas for the evaluation of the learning effect.