Literature on association mining, the data mining methodology that investigates associations between items, has primarily focused on efficiently mining larger databases. The motivation for association mining is to use the rules obtained from historical data to influence future transactions. However, associations in transactional processes change significantly over time, implying that rules extracted for a given time interval may not be applicable for a later time interval. Hence, an analysis framework is necessary to identify how associations change over time. This paper presents such a framework, reports the implementation of the framework as a tool, and demonstrates the applicability of and the necessity for the framework through a case study in the domain of finance.
Çinicioğlu, E. N., Ertek, G., Demirer, D., Yörük, E., (2011) “A Framework for Automated Association Mining Over Multiple Databases”. Proceedings of International Symposium on Innovations in Intelligent Systems and Applications 2011. (IEEE). June 15-17, 2011, Istanbul, Turkey.
Note: This is the final draft version of this paper. Please cite this paper (or this final draft) as above.
Download
A Framework for Automated Association Mining Over Multiple Databases
Dr. Gürdal Ertek recommends the following related books:
- Data Mining: Concepts and Techniques, Third Edition (The Morgan Kaufmann Series in Data Management Systems) 3rd Edition
- Analyzing Social Media Networks with NodeXL: Insights from a Connected World 1st Edition
- Post-mining of Association Rules: Techniques for Effective Knowledge Extraction 1st Edition