Clustering has typically been a problem related to numerical data. However, in databases, oftentimes the data values are categorical and cannot be assigned meaningful numerical substitutes. With the recent interest in data mining, we begin to question the possibility of clustering numerical data. Following some recent work in this area, we propose an algorithm based on dynamical systems. To our knowledge, this is the first such algorithm that can guarantee the convergence of the dynamical system, which is a very important property for successful application. We demonstrated the effectiveness of the proposed method on both real data and synthetic data. We also propose a second method based on a graph partitioning approach, for which a new definition of similarity between two nodes is tailored for categorical data. 1 Introduction Mining numerical data has received much attention in recent research in data mining. One important form of knowledge that can be derived from such da...

Discovery of association rules has been found useful in many applications. In previous work, all items in a basket database are treated uniformly. We generalize this to the case where items are given weights to reflect their importance to the user. The weights may correspond to special promotions on some products, or the profitability of different items. We can mine the weighted association rules with weights. The downward closure property of the support measure in the unweighted case no longer exists and previous algorithms cannot be applied. In this paper, two new algorithms are introduced to handle this problem. In these algorithms we make use of a metric called the k-support bound in the mining process. Experimental results show the efficiency of the algorithms for large databases.