Application Of Data Mining In Online Staff Recruitment

Staff reeruitment is the first step of human resource management.The effectiveness of staff recruitment has direct impact on the talent quality,staff turnover and the cost of Human Resource Management for an enterprise.With the development and popularization of computer and network techniques nowadays, online recruitment becomes more and more popular for both employers and applicants. However,enterprises have to process a large number of online resumes with the rapid increase of online applicants.Thus,this study is conducted in the aim of seeking an effective and efficient method to help enterprises process the resumes with shorter time,less work load and higher screening accuracy.Quantitative and qualitative analysis are adopted in this study.Key words are extracted by position type from online resumes and then preprocessed in EXCEL.The preprocessed data are further analyzed in the Clementine software through two data mining methods - Decision Tree and Neural Networks algorithm to abstract the common features of the qualified applicants,thus providing guideline to enterprises for future online resume screening.Furthermore,comparison between these two different data mining algorithms shows that Decision Tree algorithm is superior in two aspects:faster computing speed and more understandable classification principles, while Neural Networks algorithm requires less knowledge on mathematics and statistics from users and provides higher classification accuracy.