2001 Fiscal Year Final Research Report Summary
Marketing Models for Customer Relationship
| Project/Area Number |
11480093
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
社会システム工学
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
MORI Masao Tokyo Institute of Technology, Graduate School of Decision Science and Technology, Professor, 大学院・社会理工学研究科, 教授 (80016568)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SATOMURA Takuya Osaka University, Graduate School of Economics, Lecturer, 大学院・経済学研究科, 講師 (40324743)
IIDA Tetsuo Tokyo Institute of Technology, Graduate School of Decision Science and Technology, Research Associate, 大学院・社会理工学研究科, 助手 (20262305)
YAJIMA Yasutoshi Tokyo Institute of Technology, Graduate School of Decision Science and Technology, Associate Professor, 大学院・社会理工学研究科, 助教授 (80231645)
|
|---|
| Project Period (FY) |
1999 – 2001
|
| Keywords | marketing models / customer relationship / scan-panel data / logit models / new products / online shopping / data mining / purchase behaviour |
|---|
| Research Abstract |
In this research project we developed the following models in order to support the decision making processes of the marketing activities for constructing customer relationships : (1) acceptance processes for new products and brand choices, (2) models for constructing customers' consideration sets, (3) models for customers' variety-pursuing behaviour, (4) brand choices with purchase volumes and responses for price, (5) brand choices with time-varying responses for price, and (6) models for customers' online shopping behaviour. We evaluate these models with empirical analyzes using scan-panel data and access log data of an online site.
With the technologies used in the development of the models we segmented markets of financial products, and also developed a methodology to estimate promotion activities of retailers from scan-panel data.
Furthermore, as one of applications of the above models we developed a method to estimate preferences of customers for brands, and to map both the customers and the brands into a multi-dimensional space. With the distances in the space between the brands and the customers we can find the customers who have not purchased some brand, but have good preferences for the brand.
|
