The explosive growth of the worldwide web and the emergence of e-commerce has led to the development of recommender systems-a personalized information filtering technology used to identify a set of N items that will be of interest to a certain user. User-based collaborative filtering is the most successful technology for building recommender systems to date, and is extensively used in many commercial recommender systems. Unfortunately, the computational complexity of these methods grows linearly with the number of customers that in typical commercial applications can grow to be several millions. To address these scalability concerns item-based recommendation techniques have been developed that analyze the user-item matrix to identify relations between the different items, and use these relations to compute the list of recommendations. In this paper we present one such class of item-based recommendation algorithms that first determine the similarities between the various items and then used them to identify the set of items to be recommended. The key steps in this class of algorithms are (i) the method used to compute the similarity between the items, and (ii) the method used to combine these similarities in order to compute the similarity between a basket of items and a candidate recommender item. Our experimental evaluation on nine real datasets show that the proposed item-based algorithms are up to two orders of magnitude faster than the traditional user-neighborhood based recommender systems and provide recommendations with comparable or better quality.

In this paper we study the problem of classifying chemical compound datasets. We present a sub-structure-based classification algorithm that decouples the sub-structure discovery process from the classification model construction and uses frequent subgraph discovery algorithms to find all topological and geometric sub-structures present in the dataset. The advantage of our approach is that during classification model construction, all relevant sub-structures are available allowing the classifier to intelligently select the most discriminating ones. The computational scalability is ensured by the use of highly efficient frequent subgraph discovery algorithms coupled with aggressive feature selection. Our experimental evaluation on eight different classification problems shows that our approach is computationally scalable and outperforms existing schemes by 10% to 35%, on the average.

The problem of predicting a user's behavior on a web-site has gained importance due to the rapid growth of the world-wide-web and the need to personalize and influence a user's browsing experience. Markov models and their variations have been found well suited for addressing this problem. Of the different variations or Markov models it is generally found that higher-order Markov models display high predictive accuracies. However higher order models are also extremely complicated due to their large number of states that increases their space and runtime requirements. In this paper we present different techniques for intelligently selecting parts of different order Markov models so that the resulting model has a reduced state complexity and improved prediction accuracy. We have tested our models on various datasets and have found that their performance is consistently superior to that obtained by higher-order Markov models.

The atomic structures, growth behavior, and electronic properties of (Al 2 O 3 ) n , n = 1À10, clusters have been studied within the framework of density functional pseudopotential theory and generalized gradient approximation for the exchangeÀ correlation energy. The lowest energy isomers of these clusters show preference for 4-membered Al 2 O 2 and 6-membered Al 3 O 3 rings. There are 3-, 4-, and 5-fold coordinated Al atoms and 2-, 3-, and 4-fold coordinated oxygen atoms. The atomic structures have similarity with that of the γ-Al 2 O 3 phase and the average coordinations of Al and O atoms in clusters are much lower from the values in the ground state of α-Al 2 O 3 (corundum structure). In general, isomers with cage structures lie significantly higher in energy compared with the lowest energy structures we have obtained. The bonding characteristics for clusters of different sizes is studied using Bader charge analysis. It is found that with increasing size, the charge transfer from Al atoms to oxygen increases toward the value in bulk. Further, the infrared (IR) and Raman spectra have been calculated. For n = 4, a comparison of the calculated IR spectra for a few isomers with the available experimental results on cation shows the possibility of the occurrence of a mixture of isomers in experiments. The Raman spectra of these isomers are, however, quite different. Therefore, it is suggested that measurements on Raman spectra could give a clear indication of the isomer present in experiments.

No abstract