- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- Data mining applications for multi-channel marketing
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
Data mining applications for multi-channel marketing Johnson, Matthew
Abstract
The management of multi-channel marketing is one of the critical issues facing marketing practitioners today. The emergence of e-commerce has presented new opportunities to communicate with and serve customers. As a result, managers face uncertainties as to what is the best way to incorporate an e-commerce channel into their existing marketing strategies. Working in conjunction with a national retail chain (ABC)*[footnote: * - ABC is used here as a fictitious identifier of the retail chain], this thesis analyzes a multi-channel management situation using data mining techniques. The retailer has seven stores in major Canadian cities. In addition, ABC operates a telephone and mail order store and recently launched an online store at www.abc.ca. Preliminary analysis focused on ABC cataloging practices. Weekly sales data was analyzed using linear regression models to determine if a promotional impact could be seen in the weeks following catalog mailings. While there was no statistical evidence to support a promotional impact in the retail store sales, there was a promotional impact was found in the mail order sales. While this finding was interesting, the financial impact was modest. In order to identify opportunities with high sales and contribution potential, the focus of the analysis then shifted to customer's channel shopping patterns. A longitudinal study of customers shopping indicated that as customers increased/decreased the number of channels used, their spending increased/decreased. Financial analysis confirmed that converting single-channel customers to multi-channel would have high payoffs. To determine which customers would be most easily converted to multi-channel, logistic regression was used. Customers that were most likely to convert to multichannel displayed four characteristics: •lived more than 50km from an ABC store, •made more frequent purchases prior to becoming multi-channel •spent larger amounts of money prior to becoming multi-channel •have been a ABC customer for a longer period. The central implication is that marketing efforts should be targeted at "store shoppers more likely to go multi-channel". A campaign that achieves a 10 percent conversion to multi-channel shopping has the potential to produce a significant increase in sales.
Item Metadata
Title |
Data mining applications for multi-channel marketing
|
Creator | |
Publisher |
University of British Columbia
|
Date Issued |
2002
|
Description |
The management of multi-channel marketing is one of the critical issues facing marketing practitioners today. The emergence of e-commerce has presented new opportunities to communicate with and serve customers. As a result, managers face uncertainties as to what is the best way to incorporate an e-commerce channel into their existing marketing strategies. Working in conjunction with a national retail chain (ABC)*[footnote: * - ABC is used here as a fictitious identifier of the retail chain], this thesis analyzes a multi-channel management situation using data mining techniques. The retailer has seven stores in major Canadian cities. In addition, ABC operates a telephone and mail order store and recently launched an online store at www.abc.ca. Preliminary analysis focused on ABC cataloging practices. Weekly sales data was analyzed using linear regression models to determine if a promotional impact could be seen in the weeks following catalog mailings. While there was no statistical evidence to support a promotional impact in the retail store sales, there was a promotional impact was found in the mail order sales. While this finding was interesting, the financial impact was modest. In order to identify opportunities with high sales and contribution potential, the focus of the analysis then shifted to customer's channel shopping patterns. A longitudinal study of customers shopping indicated that as customers increased/decreased the number of channels used, their spending increased/decreased. Financial analysis confirmed that converting single-channel customers to multi-channel would have high payoffs. To determine which customers would be most easily converted to multi-channel, logistic regression was used. Customers that were most likely to convert to multichannel displayed four characteristics:
•lived more than 50km from an ABC store,
•made more frequent purchases prior to becoming multi-channel
•spent larger amounts of money prior to becoming multi-channel
•have been a ABC customer for a longer period.
The central implication is that marketing efforts should be targeted at "store shoppers more likely to go multi-channel". A campaign that achieves a 10 percent conversion to multi-channel shopping has the potential to produce a significant increase in sales.
|
Extent |
3413370 bytes
|
Genre | |
Type | |
File Format |
application/pdf
|
Language |
eng
|
Date Available |
2009-10-07
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.
|
DOI |
10.14288/1.0090857
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2002-11
|
Campus | |
Scholarly Level |
Graduate
|
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.