Prediction of members’ repurchase rates with time weight function

機構典藏 > College of Engineering > Graduate Institute & Department of Computer Science and Information Engineering > Journal Article > Item 987654321/92489

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/92489

Title:	Prediction of members’ repurchase rates with time weight function
Authors:	Chen, Chun-Hao;Chiang, Rui-Dong;Wong, Yi-Hsin;Chu, Huan-Chen
Contributors:	淡江大學資訊工程學系
Keywords:	CRM customer profile;Time function;Concept drift;Repurchase rate prediction
Date:	2013-09-01
Issue Date:	2013-10-16 15:00:09 (UTC+8)
Publisher:	Heidelberg: Springer
Abstract:	Customer relationship management (CRM) leverages historical users’ behaviors to dawn effort of enhancing customer satisfaction and loyalty. Thus, constructing a successful customer profile plays a critical role in CRM. In this study, we are expected to predict the repurchase rates for the registered members at the specific category of e-shop. However, customers’ preferences change over time. To capture the preference drifts of the members, we propose a novel and simple time function to increase/decrease the weight of the old data in evaluating various members’ past behaviors. Then, we construct a repurchase index with time factor (RIT) model to effectively predict repurchase rates. The marketers of e-shop can thus target the members with high repurchase rates. Experimental results with a real dataset have demonstrated that this RIT model can be practically implemented and provide satisfactory results.
Relation:	Soft Computing 17(9), pp.1711-1723
DOI:	10.1007/s00500-013-0987-9
Appears in Collections:	[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
1432-7643_17(9)p1711-1723.pdf		1869Kb	Adobe PDF	169	View/Open
index.html		0Kb	HTML	224	View/Open