In this overview paper we motivate the need for and research issues arising from a new model of data processing. In this model, data does not take the form of persistent relations, but rather arrives in multiple, continuous, rapid, time-varying data streams. In addition to reviewing past work relevant to data stream systems and current projects in the area, the paper explores topics in stream query languages, new requirements and challenges in query processing, and algorithmic issues.

Abstract The clustering problem is a difficult problem for the data stream domain. This is because the large volumes of data arriving in a stream renders most traditional algorithms too inefficient. In recent years, a few one-pass clustering algorithms have been developed for the data stream problem. Although such methods address the scalability issues of the clustering problem, they are generally blind to the evolution of the data and do not address the following issues: (1) The quality of the clusters is poor when the data evolves considerably over time. (2) A data stream clustering algorithm requires much greater functionality in discovering and exploring clusters over different portions of the stream. The widely used practice of viewing data stream clustering algorithms as a class of onepass clustering algorithms is not very useful from an application point of view. For example, a simple one-pass clustering algorithm over an entire data stream of a few years is dominated by the outdated history of the stream. The exploration of the stream over different time windows can provide the users with a much deeper understanding of the evolving behavior of the clusters. At the same time, it is not possible to simultaneously perform dynamic clustering over all possible time horizons for a data stream of even moderately large volume. This paper discusses a fundamentally different philosophy for data stream clustering which is guided by application-centered requirements. The idea is divide the clustering process into an online component which periodically stores detailed summary statistics Permission to copy without fee all or part of this material is granted provided that the copies are not made or distributed for direct commercial advantage, the VLDB copyright notice and the title of the publication and its date appear, and notice is given that copying is by permission of the Very Large Data Base Endowment. To copy otherwise, or to republish, requires a fee and/or special permission from the Endowment. Proceedings of the 29th VLDB Conference, Berlin, Germany, 2003 and an offline component which uses only this summary statistics. The offline component is utilized by the analyst who can use a wide variety of inputs (such as time horizon or number of clusters) in order to provide a quick understanding of the broad clusters in the data stream. The problems of efficient choice, storage, and use of this statistical data for a fast data stream turns out to be quite tricky. For this purpose, we use the concepts of a pyramidal time frame in conjunction with a microclustering approach. Our performance experiments over a number of real and synthetic data sets illustrate the effectiveness, efficiency, and insights provided by our approach.

Most statistical and machine-learning algorithms assume that the data is a random sample drawn from a station-ary distribution. Unfortunately, most of the large databases available for mining today violate this assumption. They were gathered over months or years, and the underlying pro-cesses generating them changed during this time, sometimes radically. Although a number of algorithms have been pro-posed for learning time-changing concepts, they generally do not scale well to very large databases. In this paper we propose an efficient algorithm for mining decision trees from continuously-changing data streams, based on the ultra-fast VFDT decision tree learner. This algorithm, called CVFDT, stays current while making the most of old data by growing an alternative subtree whenever an old one becomes ques-tionable, and replacing the old with the new when the new becomes more accurate. CVFDT learns a model which is similar in accuracy to the one that would be learned by reapplying VFDT to a moving window of examples every time a new example arrives, but with O(1) complexity per example, as opposed to O(w), where w is the size of the window. Experiments on a set of large time-changing data streams demonstrate the utility of this approach.

In many recent applications, data may take the form of continuous data streams, rather than finite stored data sets. Several aspects of data management need to be re-considered in the presence of data streams, offering a new research direction for the database community. In this pa-per we focus primarily on the problem of query processing, specifically on how to define and evaluate continuous queries over data streams. We address semantic issues as well as efficiency concerns. Our main contributions are threefold. First, we specify a general and flexible architecture for query processing in the presence of data streams. Second, we use our basic architecture as a tool to clarify alternative semantics and processing techniques for continuous queries. The architecture also captures most previous work on continuous queries and data streams, as

Recently, mining data streams with concept drifts for actionable insights has become an important and challenging task for a wide range of applications including credit card fraud protection, target marketing, network intrusion detection, etc. Conventional knowledge discovery tools are facing two challenges, the overwhelming volume of the streaming data, and the concept drifts. In this paper, we propose a general framework for mining concept-drifting data streams using weighted ensemble classifiers. We train an ensemble of classification models, such as C4.5, RIPPER, naive Bayesian, etc., from sequential chunks of the data stream. The classifiers in the ensemble are judiciously weighted based on their expected classification accuracy on the test data under the time-evolving environment. Thus, the ensemble approach improves both the efficiency in learning the model and the accuracy in performing classification. Our empirical study shows that the proposed methods have substantial advantage over single-classifier approaches in prediction accuracy, and the ensemble framework is effective for a variety of classification models.

Consider the problem of monitoring tens of thousands of time series data streams in an online fashion and making decisions based on them. In addition to single stream statistics such as average and standard deviation, we also want to find high correlations among all pairs of streams. A stock market trader might use such a tool to spot arbitrage opportunities.

Recent years have witnessed an increasing interest in designing algorithms for querying and analyzing streaming data (i.e., data that is seen only once in a fixed order) with only limited memory. Providing (perhaps approximate) answers to queries over such continuous data streams is a crucial requirement for many application environments; examples include large telecom and IP network installations where performance data from different parts of the network needs to be continuously collected and analyzed.

Classification

Although frequent-pattern mining has been widely studied and used, it is challenging to extend it to data streams. Compared to mining from a static transaction data set, the streaming case has far more information to track and far greater complexity to manage. Infrequent items can become frequent later on and hence cannot be ignored. The storage structure needs to be dynamically adjusted to reflect the evolution of itemset frequencies over time.

A major challenge in document clustering is the extremely high dimensionality. For example, the vocabulary for a document set can easily be thousands of words. On the other hand, each document often contains a small fraction of words in the vocabulary. These features require special handlings. Another requirement is hierarchical clustering where clustered documents can be browsed according to the increasing specificity of topics. In this paper, we propose to use the notion of frequent itemsets, which comes from association rule mining, for document clustering. The intuition of our clustering criterion is that each cluster is identified by some common words, called frequent itemsets, for the documents in the cluster. Frequent itemsets are also used to produce a hierarchical topic tree for clusters. By focusing on frequent items, the dimensionality of the document set is drastically reduced. We show that this method outperforms best existing methods in terms of both clustering accuracy and scalability.