Title: GAM: a guidance enabled association mining environment

Authors: Aaron Ceglar, John F. Roddick

Addresses: School of Informatics and Engineering, Flinders University of South Australia, P.O. Box 2100, Adelaide, South Australia 5001, Australia. ' School of Informatics and Engineering, Flinders University of South Australia, P.O. Box 2100, Adelaide, South Australia 5001, Australia

Abstract: The quality of data mining results is largely dependent on the ability to accommodate context and user requirements within the mining process. This is done effectively within the pre-processing and presentation stages, however the analysis (or mining) stage remains relatively autonomous and opaque with user input commonly limited to parameter setting. There is, at present, no direct manipulation of the analysis stage which results in the analysis of the domain space being statically constrained. This reduces the quality of results and increases the time needed for analysis. This paper presents a guided association mining environment, GAM, that enhances user-computer synergy by incorporating the user at fine level of granularity within the analysis stage. GAM extends the current state of the art and is based upon a generic guided knowledge discovery environment.

Keywords: guided association mining; GAM; mining process; guided knowledge discovery framework; knowledge based architecture; direct process manipulation; dataset exploration; human computer interaction; HCI; data mining.

DOI: 10.1504/IJBIDM.2007.012944

International Journal of Business Intelligence and Data Mining, 2007 Vol.2 No.1, pp.3 - 28

Published online: 31 Mar 2007 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article