Index early warning method and system based on data mining

Abstract

The invention discloses an index early warning method and system based on data mining, and the method comprises the steps: obtaining student activity time sequence data, carrying out the classification and quantification, and building a monitoring database; establishing a lasso prediction model according to the student quality index time sequence monitoring data in the monitoring database, performing index screening through the lasso prediction model, and determining a plurality of key indexes; performing multi-dimensional division on the time sequence monitoring data of the key indexes, and training a causal relationship prediction model between the key indexes and student quality and nutrition evaluation values by adopting a Granger algorithm; predicting a Granger causal score between different dimensions, different quality and nutrition indexes and student quality and nutrition evaluation values through the causal relationship prediction model; and through the Granger causality score, carrying out early warning on student quality and quality indexes. According to the invention, the causal relationship of different quality and quality indexes in different dimensions to the quality and quality evaluation values of the students can be analyzed, and index early warning can be carried out in time.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to an index early warning method and system based on data mining. Background technique [0002] The establishment of quality and literacy indicators for students in school is the main means to measure the situation of students in school. Teaching administrators not only need to pay attention to single or multiple quality indicators of individual students, but also need to divide them by units such as classes, majors, and grades. Through the comparison of different dimensions, the shortcomings in the teaching process are found, and at the same time, the problems that occur in batches are reported to the police in time, so as to correct the problems that have occurred in the past quality and literacy activities, so that they can return to the correct teaching track. [0003] Due to the large number of indicators in the traditional quality monitoring system, it needs t...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention proposes an index early warning method and system based on data mining, which is used to solve the problem that real-time early warning cannot be performed when the quality and quality indicators of students are set unreasonably

Images