A Typical Model Evaluation System for Rural Vocational Education Against Poverty Is Based on a Decision Tree Mining Algorithm

Abstract

This paper presents an in-depth study and analysis of the evaluation of typical models of rural vocational education against poverty using a decision tree mining algorithm and uses this to develop an evaluation system for practical application. The paper analyzes the teaching quality, education scale, teaching methods, and the government's policy support and financial input to local agriculture-related vocational education, and discusses the education problems behind the lack of rural talents. The concept of educational data mining is given and several common, typical decision tree algorithms are described (ID3 algorithm, C4.5 algorithm, CART algorithm, SLIQ algorithm) and the connection and difference between them; then the concept of multi-valued decision table and decision tree is discussed in detail, and the decision tree analysis method of the multi-valued decision table is given, which is primarily based on the core idea of dynamic programming and the proposed algorithm. The algorithm to minimize the size of the decision tree and then extract valuable information within the multi-valued decision table; considering the large size of the generated decision tree, the recursive algorithm to merge the identical subtrees and leaf nodes to form a decision graph is given, and the resulting decision graph has no redundant nodes. It is smaller in size, thus reducing the storage space. It is mainly caused by the weak government support for rural vocational education, the low social recognition of rural vocational education, and the limited construction level of rural vocational colleges themselves.