Research on Evaluating Teaching Quality of Accounting Courses Based on Improved K-nearest Neighbors Algorithm(KNN)

Considering the differences in clustering positions between classifiable attribute data with different occurrence times, we redefined the position of the clustering center and proposed an improved KNN clustering method. The proposed method effectively solved the problem of classifiable mixed type data. On this basis, the KNN method was applied to course teaching evaluation to study the common characteristics of different types of teaching and provide a basis for evaluating courses.