Evaluation of user satisfaction with OLAP recommender systems: an application to RecoOLAP on a agricultural energetic consumption datawarehouse

Abstract

OLAP and Datawarehouse (DW) systems are technologies intended to support the decision-making process, enabling the analysis of a substantial volume of data. Decision makers explore warehoused data using OLAP operators to discover new trends and/or confirm business hypotheses. In the era of Big Data, the size of warehoused data has increased substantially, and the data have become increasingly difficult to use. One of the goals of recommender systems is to help users navigate large amounts of data. OLAP recommender systems have recently been proposed in the literature because the multidimensional analysis process is often tedious because the user may not know what the forthcoming query should be. However, user satisfaction with these systems has not yet been investigated. Indeed, only time and space performances and classical information retrieval metrics (e.g., accuracy) have been studied on fictive DWs and users. Thus, this work is the first study of the usefulness of OLAP recommender systems from the decision maker's point of view. Indeed, to the best of our knowledge, although several works have proposed OLAP recommender systems, they did not evaluate them against real-world data and users. With our experiments on a spatial DW concerning agricultural energetic consummation issued from the Energetic French Project, we prove that OLAP recommendation is useful via a real-world case study and confirm the importance of these academic tools.

Beyond roll-up’s and drill-down’s: An intentional analytics model to reinvent OLAP

“…Assume now that the Ministry of Labor, based on the data of a previous census, has set-up some goals for the improvement of labor. Assume also that per combination of education type and workplace, a specific goal, say W eekly W orking T arget, has been assigned, saying that if the average number of weekly hours at work is in the area of [40][41][42][43][44][45][46][47][48][49][50][51][52][53][54][55] for any category, then this is Expected behavior, whereas any other amount outside this domain is either Low, or Excessive. This is exactly what business analysts call a Key Performance Indicator (KPI) Then, assume that the analyst of the Ministry wishes to evaluate the situation based on these goals, and in fact, in more details than the aggregate summary of Example 1.…”

“…The suggestion can be based on the user's profile, history of queries, history of other users' queries, or other information. Query recommendation has recently attracted many attentions for Interactive Database Exploration [44,27,32] and particularly in the case of OLAP exploration of data cubes [45,46,47,30,31,48,49], including approaches applied to spatial OLAP [50,51]. See [44,52,31,53] for a broader discussion.…”

OLAP Queries Context-Aware Recommender System

“…The recommendation approaches are popular to provide personalized results into large volumes of data [6]. However, there is few research in the field of OLAP query recommendation [7,8].…”