簡易檢索 / 詳目顯示

回結果列表
研究生： 陳慈徽
Chen, Tzu-Hui
論文名稱： 以資料探勘技術預測技術員離職傾向-以南科某公司為例
Predicting operator turnover: A multiple classifier study in the south science park
指導教授： 吳植森
Wu, Chih-Sen
學位類別： 碩士
Master
系所名稱： 管理學院 - 國際管理碩士在職進修專班(IMBA)
International Master of Business Administration(IMBA)
論文出版年： 2006
畢業學年度： 94
語文別： 英文
論文頁數： 59
中文關鍵詞： 資料探勘 、高科技 、離職傾向
外文關鍵詞： High technology, Data mining, Turnover intention
相關次數： 點閱：155  下載：16 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 　　在勞力密集的產業中，勞工為公司主要的組成份子。如何維持員工的穩定度和減少離職率是人力資源部門主要任務，但離職的原因越來越複雜和難以推估。本研究透過某半導體廠離職技術員的資料庫，藉由資料探勘技術，我們發現了擁有較高離職風險族群的隱性知識，並可依員工特質預測離職原因。
    　　就現有的輪班人員研究中，四班二輪(做二休二)亦為輪班的一種。本研究利用資料探勘技術證實三個影響特殊輪班制的因素，分別為：1. 健康 2. 家庭 3. 組織。從分析出的模式中提供公司降低離職率的政策。
    本研究主要目的為能提供公司決策參考，避免不適任人員的僱用進而降低人員離職率。在三項主要影響特殊輪班制的因素中，加上實際工作經驗交叉驗證，得到以下四項結論。
    1.　人生不再以工作為目的，健康與家庭亦必須能兼顧。
    2.　單一工作年資越來越短，擁有終生職已非工作首要目標。
    3.　高學歷高離職率(本研究中定義專科以上技術員為高學歷)。
    4.　工作滿意度與離職率呈反比。

    　　In labor-intensive industry, laborers compose the bulk of the workplace. How to keep employee levels stable and how to reduce turnover rates are a human resource department’s main tasks, especially as the reasons for quitting are getting more and more complex and unexpected. Through research, which involved data mining in a semiconductor leaving operators’ database, we discover tacit knowledge on the profile of employees who have high intension of quitting. The end result of data mining is that models or classifiers can be built and used to predict operators’ reasons for leaving.
    The existing research connects with shift workers, as well as the “four-shifts-two-turns” domain of employees. This research uses data mining technology to verify three types of consequences that have been studied in relation to shift work, relating particularly to rotating vs. fixed shifts. They are as follows: (1)　physical health variables; (2)　family and social variables; and (3)　organizational variables. Try to reveal implicit rules, then to provide organizational strategies. Through this knowledge models may be further built to reduce turnover intention.
    　　The main aim of this study is to highlight how to reduce erroneous judgment ratios of recruit and turnover rates based on mining historical databases, and hopefully provide an effective decision tool for company. The reasons for quitting have been put into three groups. We relied on those behaviors and further added working experience. Validate the following states throughout this study.
    1.　Working is not the only major issue in life. Healthy and family are more important than having a job.
    2.　A lifetime job is not a career goal. As a result of this, the job cycle is getting shorter.
    3.　Higher education causes higher turnover rate. In this research, we define high education level of operators junior college or above.
    4.　Employees not satisfied with their jobs can cause higher turnover intention.

    ACKNOWLEDGEMENTS ……………………………………………………………I ABSTRACT ………………………………………………………………………… II TABLE OF CONTENTS …………………………………………………………… IV LIST OF TABLES ………………………………………………………………… VII LIST OF FIGURES ………………………………………………………………… IX CHAPTER ONE INTRODUCTION ………………………………………………… 1 1.1 Research Background ……………………………………………………………1 1.2 Research Objectives………………………………………………………………2 1.3 Research Process …………………………………………………………………3 CHAPTER TWO LITERATURE REVIEW……………………………………………5 2.1 Turnover Intention ……………………………………………………………… 5 2.2 Impact of Shift Workers ………………………………………………………… 6 2.3 Data Mining………………………………………………………………………7 2.4 Some History of Data Analysis……………………………………………………8 2.5 Data Mining Functions……………………………………………………………9 2.5.1 Classification……………………………………………………………………9 2.5.2 Estimation………………………………………………………………………9 2.5.3 Prediction………………………………………………………………………10 2.5.4 Grouping ………………………………………………………………………10 2.5.5 Clustering………………………………………………………………………10 2.5.6 Description …………………………………………………………………… 11 2.6 Data Mining Technologies……………………………………………………… 11 2.6.1 Memory Based Reasoning (MBR) …………………………………………… 12 2.6.2 Decision Tree ………………………………………………………………… 12 2.6.3 Neural Networks……………………………………………………………… 13 2.6.4 Market Basket Analysis ……………………………………………………… 14 2.6.5 Bayesian Network …………………………………………………………… 14 CHAPTER THREE RESEARCH METHODOLOGY AND DESIGN…………………16 3.1 Research Problems and Rules……………………………………………………16 3.2 Data Mining Tool Survey ……………………………………………………… 17 3.2.1 Research Methodology ……………………………………………………… 18 3.3 Introduce WEKA Analyzer………………………………………………………19 3.3.1 Brief Introduction to An ARFF File…………………………………………… 21 3.4 An Introduction to iDA Analyzer ……………………………………………… 23 3.5 KDD Approach to Resolve The Research Problems …………………………… 28 3.6 Training and Test Datasets ………………………………………………………33 3.6.1 Oversampling …………………………………………………………………33 3.7 Research Structure……………………………………………………………… 34 CHAPTER FOUR RESEARCH RESULTS ………………………………………… 35 4.1 Data Mining and Result Evaluation………………………………………………35 4.1.1 The First Rule………………………………………………………………… 35 4.1.2 The Second Rule………………………………………………………………39 4.1.3 The Third Rule…………………………………………………………………40 4.1.4 The Fourth Rule ……………………………………………………………… 42 4.2 Result Evaluation ……………………………………………………………… 45 4.2.1 WEKA Bayesian Network …………………………………………………… 45 4.2.2 Supervised Learning ………………………………………………………… 50 4.3 Summary…………………………………………………………………………53 CHAPTER FIVE CONCLUSIONS ANDSUGGESTIONS……………………………54 5.1 Conclusion……………………………………………………………………… 54 5.2 Suggestions………………………………………………………………………54 5.3 Limitations……………………………………………………………………… 55 REFERENCES ………………………………………………………………………57

    Aaron, C. (2000). The relationship between commitment forms and work outcomes: A comparison of three models. Human Relations, 53(3), 387.
    Ajzen, I. (1991). The theory of planned behavior. Organizational Behavior and Human Decision Processes, 50(2), 179.
    Alfonso, S., & Fred, H. (2004). Analyzing job mobility with job turnover intentions: An international comparative study. Journal of Economic Issues, 38(1), 113.
    Alhoniemi, E., Hollmen, J., Simula, O., & Vesanto, J. (1999). Process monitoring and modeling using the self-organizing map. Integrated Computer-Aided Engineering, 6(1), 3.
    Anonymous. (2001). A new worry for women shiftworkers. The Worklife Report, 13(4), 9.
    Berry, M. J. A., & Linoff, G. (1997). Data mining techniques: For marketing, sales, and customer support. New York: Wiley.
    Berry, M. J. A., & Linoff, G. (2000). Mastering data mining: The art and science of customer relationship management. New York Wiley Computer Pub.
    Berzal, F., Blanco, I., Cubero, J., & Marin, N. (2002). Component-based data mining frameworks. Communications of the ACM, 45(12), 97-100.
    Blanche, G. (2004). The effects of shift work on family satisfaction. Families in Society, 85(3), 413.
    Blau, G., & Lunz, M. (1999). Testing the impact of shift schedules on organizational variables. Journal of Organizational Behavior, 20(6), 933.
    Bohle, P., & Tilley, A. J. (1998). Early experience of shiftwork: Influences on attitudes. Journal of Occupational & Organizational Psychology, 71(1), 61-79.
    Chang, L. Y., Yao, H. Y., Hou, J. L., He, P. X., & Xu, F. Q. (2003). Customer relationship managerment. Hwatai.
    Demerouti, E., Guerts, S. A. E., Bakker, A. B., & Euwema, M. (2004). The impact of shiftwork on work-home conflict, job attitudes and health. Ergonomics, 47(9), 987-1002.
    Elidan, G., Friedman, N., & Chickering, D. M. (2005). Learning hidden variable networks: The information bottleneck approach. Journal of Machine Learning Research, 6(1), 81-127.
    George, J. M., & Jones, G. R. (1996). The experience of work and turnover intentions: Interactive effects of value attainment, job satisfaction, and positive mood. Journal of Applied Psychology, 81(3), 318.
    Haar, J. M. (2004). Work-Family conflict and turnover intention: Exploring the moderation effects of perceived work-family support. New Zealand Journal of Psychology, 33(1), 35-39.
    Han, J., & Kamber, M. (2001). Data mining: Concepts and Techniques. San Francisco: Morgan Kaufmann Publishers.
    Hirji, K. K. (2001). Exploring data mining implemention. Communications of the ACM, 44(7), 87-93.
    Houkes, I., Janssen, P. P. M., de Jonge, J., & Bakker, A. B. (2003). Specific determinants of intrinsic work motivation, emotional exhaustion and turnover intention: A multisample longitudinal study. Journal of Occupational & Organizational Psychology, 76(4), 427-450.
    Kasif, S., Salzberg, S., Waltz, D., Rachlin, J., & Aha, D. W. (1998). A probabilistic framework for memory-based reasoning. Artificial Intelligence 104(1-2 ), 287-311
    Lac, G., & Chamoux, A. (2004). Biological and psychological responses to two rapid shiftwork schedules. Ergonomics, 47(12), 1339.
    Mitra, S., & Acharya, T. (2003). Data mining: multimedia, soft computing, and bioinformatics. Hoboken, NJ: Wiley.
    Mobley, W. H. (1977). Intermediate linkages in the relationship between job satisfaction and employee turnover. Journal of Applied Psychology, 62(2), 237.
    Morrison, R. (2004). Informal relationships in the workplace: Associations with job satisfaction, organizational commitment and turnover intentions. New Zealand Journal of Psychology, 33(3), 114-128.
    Pappas, A. (2001). The accuracy of a bayesian network. University of London, London.
    Pearl, J. (1997). Probabilistic reasoning in intelligent systems: Bnetworks of plausible inference. San Mateo, Calif.: Morgan Kaufmann Publishers.
    Rabiul, A., Golam, M., & Abdul, K. (2002). Psychosocial implications of shift work: A case study. Work Study, 51(2/3), 116.
    Roiger, R., & Geatz, M. (2003). Data mining: A tutorial-based primer. Boston: Addison Wesley.
    Sung, H. H., & Sang, C. P. (1998). Application of data mining tools to hotel data mart on the Intranet for database marketing Expert Systems with Applications 15(1), 1-31.
    Witten, I. H., & Frank, E. (2000). Data mining: Practical machine learning tools and techniques with java implementations. San Francisco: Morgan Kaufmann.
    Zhang, S., Zhang, C., & Yang, Q. (2003). Data preparation for data mining. Applied Artificial Intelligence, 17(5/6), 375.

    下載圖示 校內：立即公開
    校外：2006-08-25公開
    QR CODE