Inter-Purchase Time Model for Multi-Category Products : Take Amazon.com for Example

• Main Authors: Ding-Jyun Huang, 黃鼎鈞
• Other Authors: Ching-I Cheng
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/04416933476266875648

碩士 === 國立暨南國際大學 === 國際企業學系 === 101 === There are more and more competitors in the market in recent years, how to enhance consumer’s loyalty to maintain a long-term and sustained relationship has become an important issue of manufacturers. Manufacturers can use customer database to do the one-to-one marketing by data mining, and use market basket analysis to recommend the right products to the consumers. However, the past research ignored the forecast of the Inter-Purchase Time and the situation of consumers bought two products at the same time. This research establishes a model which can integrate inter-purchase time and multi-category purchase choices. This research use a mixture log-normal regression model to establish a inter-purchase time model for multi-category products, which can predict the purchase behavior of consumer more accurately than the purchase timing model for single products when customers bought two products at the same time. This research uses the transaction records of consumers done in Amazon.com in 2010 and 2011 that recorded in Comscore database to do the empirical research. Finding the inter-purchase time from books to movie is shorter than the inter-purchase time from movies to books. According to the model analysis and empirical results, this research finally propose the applications and recommendations in the management.