International Journal of Computer Science & Information Technology (IJCSIT), Vol 3, No 3, June 2011 DOI : 10.5121/ijcsit.2011.3320 275       Nadia Mesghouni 1 Khaled Ghedira 2 and Moncef Temani 3 1 University of Tunis Laboratory LI3 ISG Tunis, Tunis, Tunisie nadia.mesghouni@yahoo.fr 2 University of Tunis Laboratory LI3 ISG Tunis, Tunis, Tunisie Khaled.ghdira@isg.rnu.tn 3 University of Tunis Laboratory LI3 ISG Tunis, Tunis, Tunisie Moncef.temanni@fst.rnu.tn ABSTRACT In this paper we present a new approach of collaborative classification allowing protecting the confidentiality of the data by using the self organizing map of Kohonen. Having a collection of databases distributed on several different sites, so, the problem consists in clustering each of these bases by considering the data and the classifications of the others base co- workers, without omitting however to respect the constraint of confidentiality which forbids the sharing of data between the various centers. To do it, our approach is subdivided into two phases: a local phase and a collaborative phase. The local phase would mean applying the classic algorithm of Kohonen, locally and independently on each of the databases, what will end in the obtaining of a map (SELF-ORGANIZING MAP) for each of these bases. The phase of collaboration would mean making each of the databases collaborate with all the map SOM partners in the other bases obtained during the local phase. So, as result we obtain on each of the sites a map close to the SOM which we would have obtained if we had disregarded the constraint of confidentiality, namely make databases collaborate they same. In the stemming from both phases, all the maps will be enriched. The article presents the formalism of the approach as well as its validation. The proposed approach was validated on several databases and the experimental results showed very promising performances. KEYWORDS Self organizing Map, unsupervised learning, collaborative classification, confidentiality of data 1. INTRODUCTION In an industrial context of increasing competition, companies are constantly called up on to work together (to collaborate) to face up to this strategic issue and to be able to provide the level of required service for their customers. To benefit from this collaboration, the tasks of Data Mining (Clustering, mining and knowledge management ...) should consider all the datasets associated with these collaborating companies although they are distributed on several different sites. Obviously, for confidentiality reasons (ex. medical or bank data), sharing data between collaborating companies is not allowed. So, centralizing their data by combining them into one dataset and then performing the task of Data Mining is not appropriate. In this paper, we are interested in the problem of clustering and specifically in collaborative clustering preserving data confidentiality and using self organizing maps of Kohonen.[1] The rest of this article is organized as follows: we’ll present our vertical collaboration approach in section 2, after introducing the problem of collaborative clustering. In Section 3, we’ll present different results. Finally, we completed by the conclusion. .