Personnalisation d'analyses décisionnelles sur des données multidimensionnelles

This thesis investigates OLAP analysis personalization within multidimensional databases.OLAP analyse is modeled through a graph where nodes represent the analysis contexts andgraph edges represent the user operations. The analysis context regroups the user query aswell as result. It is well described by a specific tree structure that is independent on thevisualization structures of data and query languages. We provided a model for userpreferences on the multidimensional schema and values. Each preference is associated with aspecific analysis context. Based on previous models, we proposed a generic framework thatincludes two personalization processes. First process, denoted query personalization, aims toenhancing user query with related preferences in order to produce a new one that generates apersonalized result. Second personalization process is query recommendation that allowshelping user throughout the OLAP data exploration phase. Our recommendation frameworksupports three recommendation scenarios, i.e., assisting user in query composition, suggestingthe forthcoming query, and suggesting alternative queries. Recommendations are builtprogressively basing on user preferences.In order to implement our framework, we developed a prototype system that supports querypersonalization and query recommendation processes. We present experimental resultsshowing the efficiency and the effectiveness of our approaches.