N. Mozafari, S. Hashemi & A. Hamzeh International Journal of Data Engineering (IJDE), Volume (2) : Issue (1) : 2011 16 On Tracking Behavior of Streaming Data: An Unsupervised Approach Niloofar Mozafari mozafari@cse.shirazu.ac.ir Department of Computer Science and Engineering and Information Technology Shiraz University Shiraz, Iran Sattar Hashemi s_hashemi@shirazu.ac.ir Department of Computer Science and Engineering and Information Technology Shiraz University Shiraz, Iran Ali Hamzeh ali@cse.shirazu.ac.ir Department of Computer Science and Engineering and Information Technology Shiraz University Shiraz, Iran Abstract In the recent years, data streams have been in the gravity of focus of quite a lot number of researchers in different domains. All these researchers share the same difficulty when discovering unknown pattern within data streams that is concept change. The notion of concept change refers to the places where underlying distribution of data changes from time to time. There have been proposed different methods to detect changes in the data stream but most of them are based on an unrealistic assumption of having data labels available to the learning algorithms. Nonetheless, in the real world problems labels of streaming data are rarely available. This is the main reason why data stream communities have recently focused on unsupervised domain. This study is based on the observation that unsupervised approaches for learning data stream are not yet matured; namely, they merely provide mediocre performance specially when applied on multi-dimensional data streams. In this paper, we propose a method for Tracking Changes in the behavior of instances using Cumulative Density Function; abbreviated as TrackChCDF. Our method is able to detect change points along unlabeled data stream accurately and also is able to determine the trend of data called closing or opening. The advantages of our approach are three folds. First, it is able to detect change points accurately. Second, it works well in multi-dimensional data stream, and the last but not the least, it can determine the type of change, namely closing or opening of instances over the time which has vast applications in different fields such as economy, stock market, and medical diagnosis. We compare our algorithm to the state-of-the-art method for concept change detection in data streams and the obtained results are very promising. Keywords: Data Stream, Trend, Concept Change, Precision, Recall, F1 Measure, Mean Delay Time. 1. INTRODUCTION Recently, data streams have been extensively investigated due to the large amount of applications such as sensor networks, web click streams and network flows [1], [2], [3], [4], [5]. Data stream is an ordered sequence of data with huge volumes arriving at a high throughput that must be analyzed in a single pass [6], [7]. One of the most important challenges in data streams