SMART: Semantic multidimensional group recommendations

The rising availability of data in the information systems has boosted the challenging problem of queries recommendation, especially in OLAP systems. In this paper, we introduce an innovative 𝓢ℳ𝓐𝓡𝓣 system for semantic multidimensional group recommendations to enhance the querying formulation process. Indeed, we describe the problem of group recommendation and define its semantics through introducing our group profiling ontology. Thus, we infer the analysts’ ongoing behaviors on our ontological concepts using a weighted summation strategy. Based on our ontological representation, we propose a new method for deriving relevant semantic recommendations (i.e., complete and queries fragments). In addition, an optimization technique for selecting the most interesting visualization of recommendations is proposed. Carried out experiments of our 𝓢ℳ𝓐𝓡𝓣 system on real built financial data warehouse highlight encouraging results in terms of precision and recall.

[1]  Stefano Spaccapietra,et al.  Modular Ontologies: Concepts, Theories and Techniques for Knowledge Modularization , 2009, Modular Ontologies.

[2]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[3]  Thomas R. Gruber,et al.  Toward principles for the design of ontologies used for knowledge sharing? , 1995, Int. J. Hum. Comput. Stud..

[4]  Arnaud Giacometti,et al.  Recommending Multidimensional Queries , 2009, DaWaK.

[5]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[6]  Faïez Gargouri,et al.  Building MultiView Analyst Profile From Multidimensional Query Logs: From Consensual to Conflicting Preferences , 2012, ArXiv.

[7]  Neoklis Polyzotis,et al.  The QueRIE system for Personalized Query Recommendations , 2011, IEEE Data Eng. Bull..

[8]  Neoklis Polyzotis,et al.  SQL QueRIE recommendations , 2010, Proc. VLDB Endow..

[9]  Kostas Stefanidis,et al.  gRecs: Exploiting the Power of Data Mining Techniques for Efficient Computation of Group Recommendations , 2013, ERCIM News.

[10]  Evaggelia Pitoura,et al.  Finding the Right Set of Users: Generalized Constraints for Group Recommendations , 2013, ArXiv.

[11]  Faiez Gargouri,et al.  Building Con?ict-Aware Profiling Ontology from Data Warehouses , 2012 .

[12]  Olivier Teste,et al.  Preference-Based Recommendations for OLAP Analysis , 2009, DaWaK.

[13]  Faïez Gargouri,et al.  A Survey of User-Centric Data Warehouses: From Personalization to Recommendation , 2011, ArXiv.

[14]  Arnaud Giacometti,et al.  Query recommendations for OLAP discovery driven analysis , 2009, DOLAP.

[15]  M. Golfarelli.  From User Requirements to Conceptual Design in Data Warehouse Design , 2009 .

[16]  Matteo Golfarelli.  From User Requirements to Conceptual Design in Warehouse Design: A Survey , 2010 .

[17]  Matteo Golfarelli,et al.  myOLAP: An Approach to Express and Evaluate OLAP Preferences , 2011, IEEE Transactions on Knowledge and Data Engineering.

[18]  Fadila Bentayeb,et al.  Interactive Query Recommendation Assistant , 2012, 2012 23rd International Workshop on Database and Expert Systems Applications.

[19]  Olivier Teste,et al.  Applying Recommendation Technology in OLAP Systems , 2009, ICEIS.