Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Exploring data mining implementation
Hirji K. Communications of the ACM44 (7):87-93,2001.Type:Article
Date Reviewed: Sep 1 2001

This case study addresses the potential and usefulness of data mining for decision making. The study was undertaken at TAKCO, a North American fast food retailer. The data mining methodology of Cabena et al. is followed. This methodology consists of the following stages: business objectives determination, data preparation, data mining, results analysis, and knowledge assimilation. The author assesses this methodology and presents some interesting extensions to prevent data mining projects from failing.

In the introduction, the author discusses the emergence of data mining and its potential to create competitive advantage. He clearly indicates the need for research on how to do data mining. The following section provides a brief overview of some important data mining concepts. The research methodology is described next; both the case study approach and the data collection procedure are outlined.

The case study analysis forms the heart of the article. The author found three project discontinuities that appear when using the methodology of Cabena et al.: anticipation, anxiety, and frustration. The additional data audit and back-end data mining steps are suggested as solutions to these problems. In a concluding section, the author indicates the need for more case study research to confirm the general validity of his findings.

Although the article is clearly written and well structured, it would have benefited from the discussion of more popular methodologies, such as CRISP-DM, and the inclusion of more quantitative results.

Reviewer:  B. Baesens Review #: CR125337
Bookmark and Share
Would you recommend this review?
Other reviews under "Data Mining": Date
A scalable, incremental learning algorithm for classification problems
Ye N., Li X. Computers and Industrial Engineering 43(4): 677-692, 2002. Type: Article, Reviews: (1 of 2)
Jun 4 2003
A New Method for Mining Regression Classes in Large Data Sets
Leung Y., Ma J., Zhang W. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(1): 5-21, 2001. Type: Article
Mar 1 2002
A bit level representation for time series data mining with shape based similarity
Bagnall A., Ratanamahatana C., Keogh E., Lonardi S., Janacek G. Data Mining and Knowledge Discovery 13(1): 11-40, 2006. Type: Article
Apr 10 2007

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 2004™
Terms of Use
| Privacy Policy