基于分类算法的互联网招聘岗位申请率预测分析  

Prediction and Analysis of Job Application Rate of Internet Recruitment Based on Classification Algorithm

作　　者：李佳容 Li Jiarong(Shandong University of Finance and Economics,Ji’nan Shandong 250014)

机构地区：[1]山东财经大学,山东济南250014

出　　处：《山东纺织经济》2022年第12期17-19,29,共4页Shandong Textile Economy

摘　　要：随着大数据及网络科技的不断发展,互联网招聘成为招聘的一种重要方式,而如何为求职者合理提供职位等需求都是网上招聘的难题所在。为解决这一现实问题,文章从申请岗位数据推荐需求出发,基于数据挖掘和机器学习中的分类算法,依托python技术,设计与建立了由描述接近度、城市匹配度、一般工龄等指标与是否岗位申请率关联的预测模型,并对各个算法的预测准确率与可伸缩性进行分析和比较。试验结果表明,朴素贝叶斯算法具有较好的分类速度和分类效果,能更好地分析出数据中影响求职者选择岗位的因素,预测招聘岗位的申请率,为用人单位提供优质信息,缩短了筛选时间,提升了用户体验。With the continuous development of big data and network technology, Internet recruitment has become an important way of recruitment, and how to provide job seekers with reasonable positions and other needs is the problem of online recruitment. In order to solve this practical problem, this paper starts from the demand of data recommendation of applying for job, based on the classification algorithm in data mining and machine learning, and relying on Python technology, designs and establishes a prediction model that describes whether the proximity, city matching, general length of service and other indicators are related to the job application rate, and analyzes and compares the prediction accuracy and scalability of each algorithm.The experimental results show that naive Bayesian algorithm has better classification speed and classification effect, can better analyze the factors that affect job seekers’ selection of positions in the data, predict the application rate of recruitment positions,provide high-quality information for employers, shorten the screening time, and improve the experience of users.

关 键 词：朴素贝叶斯 分类算法 预测分析 机器学习 互联网招聘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]