Detail Which visits lead to purchases? Decomposing the buying process into visiting and conversion behavior Bibliografi Author: Moe, Wendy W. ; Fader, Peter S. (Advisor) Topik: BUSINESS ADMINISTRATION; MARKETING Bahasa: (EN )    ISBN: 0-599-82172-8     Penerbit: University of Pennsylvania Press     Tahun Terbit: 2000     Jenis: Theses - Dissertation Fulltext: 9976457.pdf (0.0B; 6 download) Abstract When studying consumer buying behavior, most marketing models have focused on purchasing events only and ignored much of the information provided by visiting patterns. One reason for this is that purchases are easily observable whereas visits, especially those not associated with a purchase, are not. However, with the Internet and the emergence of e-commerce, marketers are able to observe more than just what and when consumers purchased, but they can also observe the individual store visiting patterns that affect purchasing. The richness of this information has the potential to provide marketers with an in-depth understanding of consumer shopping processes and the ability to more effectively segment and target consumers. Using commonly available clickstream data, this dissertation examines both visiting and purchasing patterns at the individual level. By decomposing the buying process into a pattern of visits and purchase conversion at each visit, we can better understand the relationship between consumer visiting and purchasing patterns. This allows us to more accurately forecast a shopper's future behavior (both visits and purchases) at the site and hence determine the value of individual customers to the site. In this dissertation, I will show that individual patterns of visits provide valuable information about consumers' purchasing tendencies and their value as customers. Additionally, I will show that forecasts of purchasing behavior are more accurate when visiting patterns are incorporated into the model than when purchases are modeled in the absence of any visiting information. This dissertation will develop two separate models, one of individual visiting behavior and one of conversion probabilities. Both models will allow for non-stationarity. The evolving visit (EV) model examines the timing of each individual's sequence of visits. It allows individual households to change their rate of visiting over time, as well as drop out and stop visiting all together, as they gain experience with the site. The second model developed in this dissertation is one of conversion behavior, or purchasing probability at each visit. Given a sequence of visits, this dissertation will model individual conversion probabilities at each of the visits and examine how they change from visit to visit. The final piece of the dissertation will combine the two models in an effort to better forecast purchasing. Opini Anda Klik untuk menuliskan opini Anda tentang koleksi ini! Lihat Sejarah Pengadaan  Konversi Metadata   Kembali

Copyright © 2006, 2007 Unika Atma Jaya, all rights reserved