任立中2006-07-262018-06-292006-07-262018-06-292000http://ntur.lib.ntu.edu.tw//handle/246246/17007http://ntur.lib.ntu.edu.tw/bitstream/246246/17007/1/892416H002055.pdfDirect marketers are often faced with the task of ranking, or scoring individual customers in terms of their expected value to the firm. A critical element of these scoring systems is expected frequency of customer interaction. In this paper the authors develop a hierarchical Bayes model of purchase frequency that combines a Poisson likelihood with a gamma mixing distribution, where is mixing distribution is a function of covariates. The proposed model is evaluated with two direct marketing datasets, and is shown to provide improved estimates of purchase frequency, particularly for customers with short purchase histories or who have infrequent interaction with the firm.application/pdf115909 bytesapplication/pdfzh-TW國立臺灣大學國際企業學系暨研究所reporthttp://ntur.lib.ntu.edu.tw/bitstream/246246/17007/1/892416H002055.pdf