河北大学学报(自然科学版) ›› 2018, Vol. 38 ›› Issue (1): 99-104.DOI: 10.3969/j.issn.1000-1565.2018.01.015

• • 上一篇    下一篇

基于期望值简约的模糊非线性回归

刘照   

  • 收稿日期:2017-06-11 出版日期:2018-01-25 发布日期:2018-01-25
  • 作者简介:刘照(1989—),女,河北保定人,河北金融学院助教,主要从事计算机应用、数据挖掘方向研究. E-mail: liuzhaozhao@sina.com
  • 基金资助:
    河北省人力资源和社会保障研究课题(JRS-2016-1085);河北省人才工程培养经费资助科研项目(A2017002116)

Empirical study on a prediction model for the unemployment rate of college graduates based on principal component analysis and BP neural network

LIU Zhao   

  1. Financial Synergy Innovation of Science and Technology Center in Hebei Province, Hebei Finance University, Baoding 071051, China
  • Received:2017-06-11 Online:2018-01-25 Published:2018-01-25

摘要: 针对高校毕业生失业数据的非线性、小样本、高维度特点,采用主成分分析和BP神经网络相结合的方法,构建了高校毕业生失业率预测模型,并借助河北省1995—2016年高校毕业生失业数据进行了实证研究.结果表明,该模型能有效地反映河北省高校毕业生失业率的变化趋势,预测精度高于仅用BP神经网络构建的预测模型.

关键词: 主成分分析, BP神经网络, 高校毕业生, 失业率预测

Abstract: A prediction model for the unemployment rate of college graduates was developed based on principal component analysis and BP neural network, followed by analyzing the unemployment data of college graduates in Hebei province in the years 1995—2016.The results show that the model can effectively reflect the variation tendency of the unemployment rate of college graduates in Hebei province and the prediction accuracy of the model is higher than that of the model only based on BP neural network.

Key words: principal component analysis, BP neural network, college graduate, unemployment rate prediction

中图分类号: