Online Mining of Changes from Data Streams: Research Problems and Preliminary Results

Document Type


Publication Date



As data streams are gaining prominence in a growing number of emerging applications, advanced analysis and mining of data streams is becoming increasingly important. While there are some recent studies on mining data streams, we would like to ask the following essential question: What are the distinct features of mining data streams compared to mining other kinds of data? In this paper, we take the following position: online mining of the changes in data streams is one of the core issues. We propose some interesting research problems and highlight the inherent challenges. Moreover, we sketch some preliminary results.


Presented at the Center for Discrete Mathematics & Theoretical Computer Science Workshop on Management and Processing Data Streams, San Diego, CA, June 8, 2003.