摘要
大数据时代下,处理已知和预测未知数据的数据挖据技术在社会生活的众多方面得到了大量应用。因此,采用数据挖据中BP神经网络算法和决策树技术对毕业生就业偏好进行了预测研究。研究中首先对两种算法流程进行了介绍,其次应用两种算法分别对扬州大学2017年本科毕业生就业情况进行模拟预测研究,并对两种算法优缺点和结果进行了对比分析。通过模拟预测结果得知,两种算法预测数据均与实际吻合,决策树法更适用于数据数量较少的样本,而当数据量较大时,BP神经网络法得到的预测数据将更准确。
Data mining technology for processing known and predicted unknown data has been widely used in many aspects of social life. Therefore,BP neural network algorithm and decision tree technique are used to predict graduatesundefined employment preference. In the study,the flow of two algorithms is introduced,and then the employment situation of graduates in 2017 is simulated and forecasted,and the advantages,disadvantages and results of the two algorithms are compared and analyzed. The simulation results show that the predicted data of the two algorithms are in good agreement with the actual data,and the decision tree method is more suitable for the sample with less data,and the prediction data obtained by BP neural network method will be more accurate when the amount of data is large.
出处
《经济研究导刊》
2018年第20期186-190,共5页
Economic Research Guide
基金
国家自然科学基金项目(11501495)
江苏省自然科学基金项目(BK20150436)
扬州大学大学生学术科技创新基金项目(201711117069X)
