Predictive Models for Employee Voluntary Turnover: An Empirical Study of a Manufacturing Company in Taiwan

NCUIR > School of Management at National Central University > Graduate Institute of Human Resource Management > Electronic Thesis & Dissertation > Item 987654321/82962

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/82962

Title:	Predictive Models for Employee Voluntary Turnover: An Empirical Study of a Manufacturing Company in Taiwan
Authors:	喬琳;Chiao, Lynn
Contributors:	人力資源管理研究所
Keywords:	機器學習;人員自願性離職;特徵選取;預測模型;監督式分類;Machine learning;Employee voluntary turnover;Feature selection;Predictive model;Supervised classification
Date:	2020-07-06
Issue Date:	2020-09-02 14:16:12 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究以台灣某製造業公司的人員資料進行分析，使用羅吉斯迴歸、支持向量機、決策樹、隨機森林和極限梯度提升這五種監督式機器學習演算法，建立人員自願性離職的預測模型。除此之外，研究同時探討不平衡資料、特徵選取與K-摺疊交叉驗證的處理技術。結果顯示，隨機森林與極限梯度提升的預測表現最佳，兩個模型的F分數與AUC值均達0.85以上，代表模型有良好的鑑別度，能有效預測人員是否會選擇離職。透過分析變數重要性，研究發現人員的年齡、年資、初階管理訓練時數、專業訓練時數與平均晉升次數皆是用來判斷人員是否會選擇離職的主要依據。關鍵詞：機器學習、人員自願性離職、特徵選取、預測模型、監督式分類 ;This study collects data from a manufacturing company in Taiwan. Logistic regression, support vector machine, decision tree, random forest, and eXtreme Gradient Boosting algorithms are adopted in order to build a reliable predictive model to predict employee voluntary turnover. Moreover, imbalanced classification problem, feature selection and K-fold cross validation are introduced and tested in this study. The results suggest random forest and eXtreme Gradient Boosting perform the best, both predictive models have the F-Score and AUC values above 0.85. Results of variable importance show elementary level of managerial training hours, professional training hours, average number of promotions, job tenure, and age contribute the most in predicting employee voluntary turnover outcome. Keywords: Machine learning, Employee voluntary turnover, Feature selection, Predictive model, Supervised classification
Appears in Collections:	[Graduate Institute of Human Resource Management ] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	243	View/Open

社群 sharing

Loading...