How to Exploit Data Mining Without Becoming Aware of it
Data mining has proved to be a valuable tool in discovering non-obvious information from a large collection of data, however in the business world is not as widely used as it could be. Common reasons include the following: (1) Data mining process requires an unbounded rationality; (2) potential end users may not be available to inform developers on what problems they are interested in or what their requirements might be; (3) high costs in the use of dating mining experts; (4) the actual result of data mining may be irrelevant or simply cannot be used. The paper presents a methodology and a system to facilitate the use of data mining in business contexts using the following approach: many models are automatically generated and stored in a database; when the end users specify some features of the model they are looking for, a search engine then retrieves any relevant models.
KeywordsData Mining Association Rule Domain Reference Data Mining Process Data Mining Model
Unable to display preview. Download preview PDF.
This work was partially supported by the Italian Government. The authors are grateful to E. Acquaviva, D. D’Antonio, G. Di Rita, A. Falossi, and M. Italiano for their implementation of the prototype system.