This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches. This paper also describes various limitations of current recommendation methods and discusses possible extensions that can improve recommendation capabilities and make recommender systems applicable to an even broader range of applications. These extensions include, among others, an improvement of understanding of users and items, incorporation of the contextual information into the recommendation process, support for multcriteria ratings, and a provision of more flexible and less intrusive types of recommendations.

This article describes a novel way of combining data mining techniques on Internet data in order to discover actionable marketing intelligence in electronic commerce scenarios. The data that is considered not only covers various types of server and web meta information, but also marketing data and knowledge. Furthermore, heterogeneity resolution thereof and Internet- and electronic commerce-specific preprocessing activities are embedded. A generic web log data hypercube is formally defined and schematic designs for analytical and predictive activities are given. From these materialised views, various online analytical web usage data mining techniques are shown, which include marketing expertise as domain knowledge and are specifically designed for electronic commerce purposes.

This article is a position paper on the nature of the data warehouse refreshment which is often defined as a view maintenance problem or as a loading process. We will show that the refreshment process is more complex than the view maintenance problem, and different from the loading process. We conceptually define the refreshment process as a workflow whose activities depend on the available products for data extraction, cleaning and integration, and whose coordination events depend on the application domain and on the required quality in terms of data freshness. Implementation of this process is clearly distinguished from its conceptual modelling. 1. Introduction Data warehousing is a new technology which provides software infrastructure for decision support systems and OLAP applications. Data warehouses collect data from heterogeneous and distributed sources. This data is aggregated and then customized with respect to organizational criteria defined by OLAP applica...

Based on a subset of the Unified Modeling Language, the authors ’ objectoriented approach to building data warehouses frees conceptual design from implementation issues. Most developers agree that data warehouse, multidimensional database (MDB), and online analytical processing (OLAP) applications emphasize multidimensional modeling, which offers two benefits. First, the multidimensional model closely parallels how data analyzers think and, therefore, helps users understand data. Second, this approach helps predict what final users want to do, thereby facilitating performance improvements. Developers have proposed various approaches for the conceptual design of multidimensional systems.

Data mining holds the key to uncovering and...

Data warehouses (DW) are built by gathering information from distributed information sources (ISs) and integrating it into one customized repository. In recent years, work has begun to address the problem of view maintenance of DWs under concurrent data updates of different ISs. Popular solutions such as ECA and Strobe achieve such concurrent maintenance however with the requirement of quiescence of the ISs. More recently, the SWEEP solution releases this quiescence requirement using a local compensation strategy that now processes all update messages in a sequential manner. To optimize upon this sequential processing, we have developed a parallel view maintenance algorithm, called PVM, that incorporates all benefits of previous maintenance approaches while offering improved performance due to parallelism. In order to perform parallel view maintenance, we have identified two critical issues: (1) detecting maintenance-concurrent data updates in a parallel mode, and (2) correcting the problem that the DW commit order may not correspond to the DW update processing order due to parallel maintenance handling. In this work, we provide solutions to both issues. Given a modular component-based system architecture, we insert a middle-layer timestamp assignment module for detecting maintenance-concurrent data updates without requiring any global clock synchronization. In addition, we introduce the negative counter concept as a simple yet elegant solution to solve the problem of variant orders of committing effects of data updates to the DW. We have proven the correctness of PVM to guarantee that our strategy indeed generates the correct final DW state. We have implemented both SWEEP and PVM in our EVE data warehousing system. Our performance study demonstrates ...

Online Analytical Processing (OLAP) data is frequently organized in the form of multidimensional data cubes each of which is used to examine a set of data values, called measures, associated with multiple dimensions and their multiple levels. In this paper, we first propose a conceptual multidimensional data model, which is able to represent and capture natural hierarchical relationships among members within a dimension as well as the relationships between dimension members and measure data values. Hereafter, dimensions and data cubes with their operators are formally introduced. Afterward, we use UML (Unified Modeling Language) to model the conceptual multidimensional model in the context of object oriented databases. 1.

Knowledge portals make an important contribution to enabling enterprise knowledge management by providing users with a consolidated, personalized user interface that allows efficient access to various types of (structured and unstructured) information. Today's portal systems allow combining access modules to different information sources side by side on a single portal webpage. However, there is no interaction between those so called portlets. When a user navigates within one portlet, the others remain unchanged, which means that each source has to be searched individually for relevant information.

this paper, three of these enabling technologies for electronic commerce are explored. First, workflow management systems for covering the process flow aspect of electronic commerce, second, database and open hypermedia technology for realizing electronic product catalogues and third, data mining technology for supporting web usage tracking. 1. Introduction

Abstract—One of the central challenges in modern science is the need to quickly derive knowledge and understanding from large, complex collections of data. We present a new approach that deals with this challenge by combining and extending techniques from high performance visual data analysis and scientific data management. This approach is demonstrated within the context of gaining insight from complex, time-varying datasets produced by a laser wakefield accelerator simulation. Our approach leverages histogram-based parallel coordinates for both visual information display as well as a vehicle for guiding a data mining operation. Data extraction and subsetting are implemented with state-of-the-art index/query technology. This approach, while applied here to accelerator science, is generally applicable to a broad set of science applications, and is implemented in a production-quality visual data analysis infrastructure. We conduct a detailed performance analysis and demonstrate good scalability on a distributed memory Cray XT4 system. I.