Informatics Publishing Limited

Miseon Lim ¹, Hyunsoo Byun ², Jinhwa Kim ¹

Affiliations
1 School of Business, Sogang University, KR
2 Department of Public Management Information Systems, Korea National University of Transportation, KR

Abstract

Understanding visitors’ invisible behaviors and responding with appropriate answers are important issues in continually increasing online market. To promote online transactions, customers’ behavior should be predicted correctly to keep low purchase conversion rate. In this study, we suggest an approach based on the idea that customers’ sessions in a web store can be transformed into the structure of a graph, which are represented as density of a session based on a graph theory. Online users visit lots of sites and their activities include information acquisition and browsing. The history of these activities can be used to construct a relationship network among web sites. This study analyzes this visit history made by website visitors with graph theory. The density of a network refers to the differentiated degrees of relationship among objects. In this study, we dichotomize into “purchase” and “no purchase group” since predicting whether a customer will buy or not buy our products is an important issue in web stores. We collect data on sessions which are a sequence of page views or a period of sustained web browsing. We model the sessions on the basis of density of a graph, which resulted in DOS (Density of a Session). The performance of other predictors including DOS is compared to that of suggested method in this study. Predictors are TVT (Total Visit Time during a period of a visit), AVT (The Average Time per Page Viewed), TNC (Total Number of Clicks), TPP (Total Number of Product-Related Pages Viewed), and DOS (Density of a Session Based on Graph Analysis). The study found that all predictors except total visit time are useful to differentiate between “purchase” and “no purchase” group. And we conducted Logit Analysis to examine the performance of each purchase prediction method. The results from Logit Analysis show that DOS predicts purchase behavior better in comparison with other predictors. It means understanding customers’ sessions with respect to a graph structure is useful to predict whether a customer will buy or not buy products in a web store.

Keywords

Click Stream Data, Predicting Customer Behavior, Web Usage Mining

Full Text

   

Sungbin Cho ¹, Jinhwa Kim ¹, Byung-Chun Ha ¹

Affiliations
1 School of Business, Sogang University, KR

Abstract

The u-government services become more personalized and intelligent. For the successful implementation of personalization, individual’s privacy must be respected and taken care of. Based on an empirical survey, this research investigates the reluctance to the government’s use of private information in six categories. We measure people’s psychological distance toward e-government using four intimacy levels suggested by the Proxemics. Since a positive correlation is identified between people’s psychological intimacy toward e-government and their tolerance to the use of private information, the amount and types of private information should be sequentially used in designing a personalization system. Beginning with the least intolerable private information such as information on one’s occupation, personalized systems should additionally use next tolerable private information such as health information or service request/interest information, as people’s psychological distance toward government services becomes shorter.

Keywords

Intimacy, Keywords4, Personalization of Service, Privacy, Ubiquitous Government

Full Text

   

Dapeng Zhao ¹, Jinhwa Kim ², Mina Woo ²

Affiliations
1 Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Guseong-dong,Yuseong-gu, Daejeon, South Korea
2 Graduate School of Business, Sogang University, 35 Baekbeom-ro, Daeheung-dong, Mapo-gu, Seoul, South Korea

Abstract

Objectives: To explore factors pertain to Smartphone users’ resistance to location-based services using data mining techniques, and to develop strategies to promote the usage of LBS. Methods: To analysis Smartphone users’ characteristics and conduct user segmentation, we used K-mean clustering to segment 165 Smartphone users based on their intimacy with service providers. Then, decision tree analysis was used to explore the characteristics for each user group. At last, the association rule analysis was used to figure out the relationship among users’ Smartphone usage patterns and their willingness to use LBS and willingness to provide location information. Findings: The result shows that Smartphone users can be clearly categorized into five groups based their intimacy towards LBS providers. The user group that showed the highest intimacy to service providers is also characterized as high willingness to use LBS and also high willingness to share their location information. Also, we explored the factors that prevent users from disclosing their location information and factors that facilitate users to use LBS for each users group respectively. The results suggest that in addition to the privacy concern, the concerns of battery life, data usage and perceived low usefulness are also accounted for users’ hesitation to share their location information to use LBS. The high needs of life information (traffic, weather and restaurant), high frequency of outdoor activities, friends’ recommendation as well as unlimited data plan were associated with users’ high intention to use LBS. Based on the association analysis result, the promotion strategies were developed for each user group respectively. Applications/Improvements: This study extends the knowledge of factors hinder users from using LBS, and also provides LBS providers with practical insights about how to promote users to a higher intimacy group.

Keywords

Association Rule Analysis, Decision-tree, Intimacy Theory, Location-based Services, User Segmentation.

Full Text