Abstract Decision-making has become a strategic need for any business. Indeed, is among the capital business priorities. The establishment of decision information systems it facilitate the data exploitation and analysis. We distinguish data warehouses as the core system of business intelligence to ensure the structuring and analysis of multidimensional data. Consequently, the design of data warehouses has become a major problem, leading... Decision-making has become a strategic need for any business. Indeed, is among the capital business priorities. The establishment of decision information systems it facilitate the data exploitation and analysis. We distinguish data warehouses as the core system of business intelligence to ensure the structuring and analysis of multidimensional data. Consequently, the design of data warehouses has become a major problem, leading to the development of appropriate approaches to implement data warehouses. In this paper, we propose an approach to design and to construct data warehouses based on a descriptive statistics technique for the analysis of multidimensional data in the Principal Components Analysis (PCA). The findings of this article appear in two main areas: (i) a conceptual model data warehouse, (ii) an algorithm for the determination of measures and dimensions. A case study is used to validate our proposal. Read More Read Less

Abstract Churners have always been a big issue for any service providing company. Churning increases cost of the company as well as decreases the rate of profit. Generally, customer attrition can be identified when they initiate the process of service termination. At the same time, the individuals and the institutions that provide the data residing on the government databases as well... Churners have always been a big issue for any service providing company. Churning increases cost of the company as well as decreases the rate of profit. Generally, customer attrition can be identified when they initiate the process of service termination. At the same time, the individuals and the institutions that provide the data residing on the government databases as well as the agencies who sponsor the collection of such information- are becoming increasingly aware that extend analytical capabilities also furnish tools that threaten the confidentiality of data records. However, using predictive analysis using customers past service usage, service performance, spending and other behavior patterns, the likelihood of whether a customer wants to terminate service can be determined. In this paper, the authors address the issue of churn analysis considering a scenario in which a company owning confidential databases wish to run a churn analysis technique on the union of their databases, without revealing any unnecessary information. The aim of the paper is to predict whether a customer will churn in the near future or not based on the predictive analysis using billing data of a telecom company. Read More Read Less

Abstract With online publications, the current Web has become the largest source of digital documents, often stored in HTML, XML, PDF or DOC. Among the features of documents, note especially their logical structure, which represents their components such as chapters, sections, paragraphs, the document title, chapter titles, sections, etc... The section headings are meaningful; they are a good indicator of the content of... With online publications, the current Web has become the largest source of digital documents, often stored in HTML, XML, PDF or DOC. Among the features of documents, note especially their logical structure, which represents their components such as chapters, sections, paragraphs, the document title, chapter titles, sections, etc... The section headings are meaningful; they are a good indicator of the content of paragraphs. For this reason we pay particular attention to these titles during the indexing process and research. Our objective is to provide relevant access to digital documents, by the process of all sections titles to take advantage of their mining and importance in the research process. Experiments on a large corpus, INEX 2009 show effectiveness of our proposition an improvement in the precision of the results in IR. Read More Read Less