Modular Neural Networks for Extending OLAP to Prediction Wiem Abdelbaki 1,2(B ) , Sadok Ben Yahia 1 , and Riadh Ben Messaoud 3 1 Faculty of Sciences of Tunis, University of Tunis El-Manar, LIPAH-LR 11ES14, 2092 Tunis, Tunisia sadok.benyahia@fst.rnu.tn 2 Department of Information Systems, College of Economics Management and Information Systems, University of Nizwa, 616 Nizwa, Nizwa, Sultanate of Oman wiem.abdelbaki@gmail.com 3 Faculty of Economics and Management of Nabeul, University of Carthage, 8000 Nabeul, Tunisia riadh.benmessaoud@fsegn.rnu.tn Abstract. On-line Analytical Processing (OLAP) represents a good applications package to explore and navigate into data cubes. Though, it is limited to exploratory tasks. It does not assist the decision maker in performing information investigation. Thus, various studies have been trying to extend OLAP to new capabilities by coupling it with data min- ing algorithms. Our current proposal stands within this trend. It has two major contributions. First, a Multi-perspectives Cube Exploration Framework (MCEF) is introduced. It is a generalized framework designed to assist the application of classical data mining algorithm on OLAP cubes. Second, a Neural Approach for Prediction over High-dimensional Cubes (NAP-HC) is also introduced, which extends Modular Neural Networks (MNN)s architecture to multidimensional context of OLAP cubes, to predict non-existent measures. A preprocessing stage is embedded in NAP-HC to assist it in facing up the challenges arising from the particu- larity of OLAP cubes. It consists of an OLAP oriented cube exploration strategy coupled with a dimensions reduction step that reposes on the Principal Component Analysis (PCA). Carried out experiments highlight the efficiency of MCEF in assisting the application of MNNs on OLAP cubes and the high predictive capabilities of NAP-HC. Keywords: Data warehouse · OLAP · Data mining · Principal Com- ponent Analysis · Multilayer Perceptrons · Modular Neural Networks 1 Introduction Data warehouses are the corner stone in the Business Intelligence (BI) roadmap. They are used to store analysis contexts within multidimensional data structures referred to as Data Cubes [1]. They are usually manipulated through On-line Analytical Processing (OLAP) applications to enable senior managers exploring information and getting BI reportings through interactive dashboards. c  Springer-Verlag Berlin Heidelberg 2015 A. Hameurlain et al. (Eds.): TLDKS XXI, LNCS 9260, pp. 73–93, 2015. DOI: 10.1007/978-3-662-47804-2 4 wiem.abdelbaki@gmail.com