Research on Talent Classification Based on Improved KNN Algorithm

With the rapid increase in the scale of colleges and universities, it is necessary to effectively classify the comprehensive quality of students, conduct stratified teaching for students, and apply KNN to the talent training in colleges and universities to provide support for the classified teaching of talent training in colleges and universities. However, the sample distribution of KNN algorithm is uneven or the sample size is too large, which affects the accuracy and efficiency of the algorithm. To solve this problem, the KNN algorithm is improved, the rough set upper and lower approximation concept is introduced to define the upper and lower approximation space of samples, and the KNN adaptive weighted classification decision function is proposed to improve the classification accuracy and efficiency. Experiments show that this method not only ensures the classification accuracy, but also improves the classification efficiency.