Application and Optimization Analysis of Decision Tree Algorithm Based on Variable Precision Rough Set

Abstract

With the huge data population of college graduates, the employment situation is complicated. How to analyze these data, the main factors affecting employment, and the results of these analysis have become the focus of research in major universities. At present, some scholars have applied algorithms such as decision tree-based, rough set-based, and rough set-based decision tree models to employment data analysis, but these algorithms cannot solve non-consistent decision tables well, but in practice, There is inconsistency in employment information. This topic mainly uses the decision tree algorithm of Variable Precision Rough Set (VPRS) to analyze the historical data of graduates, and excavates some reasonable laws that affect the employment of students, which are further applied to colleges and universities. In the employment guidance work, guide students to be more fully employed with higher quality. The decision tree algorithm is the most common method in the classification and discovery algorithm in data mining. For the different problems in the employment data, this topic mainly uses the rushing car tree algorithm of Variable Precision Rough Set (VPRS) to analyze the historical data of graduates. to dig. The method uses the measure of the classification quality of VPRS as an information function, selects conditional attributes, divides the data set from top to bottom, fully considers the dependencies and redundancy between attributes, can effectively deal with inconsistent data sets, and analyzes employment data. Reasonable classification, so as to find out the main factors affecting the employment of students, and apply the results to the employment guidance work of colleges and universities, provide decision-making suggestions and data support for college employment guidance and management, and achieve higher quality and full employment of college graduates.