以類神經網路分析探索福利制度配適化模型

NCUIR > School of Management at National Central University > Graduate Institute of Human Resource Management > Electronic Thesis & Dissertation > Item 987654321/64722

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/64722

Title:	以類神經網路分析探索福利制度配適化模型
Authors:	陳俞文;Chen,Yu-Wen
Contributors:	人力資源管理研究所
Keywords:	福利政策;工作滿意;工作投入;組織承諾;類神經網路;資料探勘技術;benefits policy;job satisfaction;job involvement;organizational commitment;neural network;data mining technique
Date:	2014-07-02
Issue Date:	2014-10-15 14:21:25 (UTC+8)
Publisher:	國立中央大學
Abstract:	在近年來企業開始重視員工福利的風氣下，公司期望制定良好的福利政策以滿足員工需求，改善員工工作滿意度、工作投入或組織承諾，最終達到提升組織績效之目的，故企業需要了解組織內員工在各類福利的需求及偏好，透過文獻探討，可以知道員工屬性是造成福利需求差異化來源之一，若企業能夠對員工屬性資料進行診斷，在切割多重屬性類別下尋找之間的差異性，必能增加組織制訂配適化模型的成效。學者針對員工在福利滿意與員工態度間之衡量多使用線性迴歸分析，然而在各項福利滿意間的互動關係或福利滿意對於員工態度可能會存在非線性關係，因此本研究希望透過系統性的資料探勘技術，對個案公司福利措施實施狀況調查及類神經網路分析了解整體福利對員工福利滿意、工作滿意、工作投入及組織承諾的配適，藉由類神經網路分析建立一套預測模式，分析員工在使用福利措施與滿意度間的行為模式，並利用重要性分析找出敏感程度較大的福利措施，提供企業在決策上的參考。研究結果發現，類神經網路分析，可以建立一套預測模式，且整體的預測率可達75%以上，實屬不錯之成效。此外，在本研究也透過重要性分析檢測企業福利制度中影響員工較大的福利項目，利用性別與婚姻狀況之員工屬性進行資料切割，可發現員工確實有不同類型的福利偏好。最後，本研究期望利用類神經網路分析提供企業系統化福利決策參考及檢測福利制度運行，未來能夠加入更多資料探勘技術，使其在應用領域上有更佳的成效。 ;In recent years, enterprises pay lots of attention on employees’ benefits and expect to satisfy employees’ requirement, improve the job satisfaction, job involvement or increase the organization commitment; in addition, the benefits system can increase the organization’s performance. Companies need to know what employees need about their benefits. By reviewing literatures, we can know that the characteristic is one of the causes of the differentiation of benefits’ need. If companies can diagnose their employees’ characteristics and figure out their differentiation, this diagnose can help construct a best model fits the organization. In the past literatures, scholars always use the multiple linear regression to examine the relationship between the satisfaction of benefits and the employees’ attitude; however, this relationship might be non-linear. This study uses the systematical data mining technique to investigate the case company’s benefits measures and uses the neural network to analyze the fits between the benefits system and employees’ satisfaction towards benefits, job satisfaction, job involvement and organizational commitment. By the neural network analysis, we can analyze the relationship between the benefits system and satisfaction; by the importance analysis, we can figure out the most sensitive benefit’s measures. Those analyses can provide enterprises as a consultation. The results find that the neural network analysis can construct a prediction model and the whole prediction rate can achieve above 75%. By the importance analysis, this study examines out the most effective benefits measures, and by the characteristics such as gender and marriage analysis, we can find employees have different preference toward the benefits measures. In conclusion, this study expects to provide the neural network analysis as a decision making tools, and hope there will be more data mining techniques to construct better outcomes.
Appears in Collections:	[Graduate Institute of Human Resource Management ] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	590	View/Open

社群 sharing

Loading...