Abstract
Organizations and firms are capturing increasingly more data about their customers, suppliers, competitors, and business environment. Most of this data is multi-attribute (multi-dimensional) and temporal in nature. Data mining and business intelligence techniques are often used to discover patterns in such data; however, mining temporal relationships typically is a complex task. We propose a new data analysis and visualization technique for representing trends in multi-attribute temporal data using a clustering-based approach. We introduce C-TREND, a system that implements the temporal cluster graph construct, which maps multi-attribute temporal data to a two-dimensional directed graph that identifies trends in dominant data types over time. In this paper, we present our temporal clustering-based technique, discuss its algorithmic implementation and performance, demonstrate applications of the technique by analyzing data on wireless networking technologies and baseball batting statistics, and introduce a set of metrics for further analysis of discovered trends.
| Original language | English (US) |
|---|---|
| Article number | 4445669 |
| Pages (from-to) | 721-735 |
| Number of pages | 15 |
| Journal | IEEE Transactions on Knowledge and Data Engineering |
| Volume | 20 |
| Issue number | 6 |
| DOIs | |
| State | Published - Jun 2008 |
Bibliographical note
Funding Information:The authors would like to thank the Digital Technology Center and the Carlson School of Management, University of Minnesota, for providing joint financial support of this research. The authors would also like to thank Prasad Sriram for his assistance with the development of the graphical user interface. Also, the research reported in this paper was supported in part by the US National Science Foundation CAREER Grant IIS-0546443.
Keywords
- Clustering
- Data and knowledge visualization
- Data mining
- Interactive data exploration and discovery
- Temporal data mining
- Trend analysis