基于数据挖掘的大学生留省就业趋势预测方法

Prediction Method of Employment Trend of College Students in Sichuan Province Based on Data Mining

当前大学生留省就业趋势预测结构多为单向,预测误差增大,为此提出基于数据挖掘的大学生留省就业趋势预测方法。首先,根据实际的预测需求及标准描述大学生就业预测问题,采用递阶方式提升预测环节的针对性;其次,建立层次预测结构,构建数据挖掘留省就业趋势预测模型,采用支持向量机(Support Vector Machine,SVM)特征归类分析实现就业趋势预测;最后,进行实验对比分析。测试结果表明,该方法的预测误差在0.2以下,说明该种预测模式更加稳定、多元,具有较高的应用价值。

At present,the prediction structure of college students' employment trends in Sichuan Province is mostly oneway,and the prediction error increases.Therefore,a data mining based method for predicting college students' employment trends in Sichuan Province is proposed.Firstly,describe the employment prediction of college students based on actual prediction needs and standards,and adopt a hierarchical approach to improve the pertinence of the prediction process.Secondly,establish a hierarchical prediction structure,construct a data mining employment trend prediction model in the province,and use Support Vector Machine(SVM) feature classification analysis to achieve employment trend prediction.Finally,experimental comparative analysis was conducted.The test results show that the prediction error of this method is below 0.2,indicating that this prediction model is more stable,multivariate,and has high application value.