Online purchase decisions for tourism e-commerce

摘要
In this study, we consider the purchase prediction problem in the context
of e-tourism, an emerging and prevailing application in e-commerce. Although a wide
array of studies have been taken on purchase prediction, little analysis has been
done on the purchasing behaviors towards tourism products. Also, the design of the
corresponding purchase prediction model deserves researchers’ full attention. We
begin by introducing a real-life e-tourism dataset and constructing a suite of variables
based on the detailed current and historical clickstream information. To validate
the effectiveness of variables, we then perform a quantitative analysis to address
quite a few interesting characteristics of purchase patterns. To predict whether
or not a purchase is made for a current visiting session, we present a novel model
called co-EM Logistic Regression (co-EM-LR) which combines the semi-supervised learning
and the multi-view learning into its procedure. The co-EM-LR model has at least
two outstanding merits: (1) it inherits the ease interpretation of the logistic
modeling; and (2) it fully exploits both unlabeled data and the compatibility of
multiple views to improve the prediction accuracy. Comprehensive experiments demonstrate
the proposed co-EM-LR model yields significant prediction performance advantages
over five competitive methods. Furthermore, two complementary views can mutually
improve the performance with each other and finally offer fast convergence.
类型
出版物
Electronic Commerce Research and Applications