Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2016, Director: Eloi Puertas i PratsAcademic tutors at universities find themselves without enough tools or material to help their students due to the lack of knowledge of each student’s academic profile. For this reason, we have performed a comprehensive study of student data in order to obtain supplementary material for the tutor. Clusterization algorithms have been used to separate the students into groups to identify general characteristics of the students belonging to a particular cluster. Dropout of each cluster and relationships between groups have been studied as well. A k-NN classifier has been used to create a prediction model which is able to predict in which cluster a student will belong the next academic year. Finally, visualization technics have been used to present the results of the analysis.