CHARACTERIZATION OF ENGINEERING STUDENT PROFILES AT EUROPEAN INSTITUTIONS BY USING SPEET IT-TOOL R. Vilanova 1 , J. Vicario 1 ,M. A. Prada 2 ,M. Barbu 3 ,M. Dominguez 3 , M. J. Varanda 4 ,M. Podpora 5 ,U. Spagnolini 6 , P. Alves 4 , A. Paganoni 6 1 Universitat Autonoma Barcelona (SPAIN) 2 Universidad de León (SPAIN) 3 University Dunarea de Jos, Galati (ROMANIA) 4 Instituto Politecnico de Bragança (PORTUGAL) 5 Opole University of Technology (POLAND) 6 Politecnico di Milano (ITALY) Abstract The international ERASMUS+ project SPEET (Student Profile for Enhancing Engineering Tutoring) aims at opening a new perspective to university tutoring systems. Before looking for its nature, it’s recommended to have a look on the current use of data in education and on the concept of academic analytics basically defined as the process of evaluating and analysing data received from university systems for reporting and decision making reasons. The provided tools are freely available to anyone that has academic data to explore. The paper will present the architecture that is behind the presented IT tool, input data needed to operate and main functionalities as well as examples of use to show how academic data can be interpreted. Keywords: International projects, International Cooperation, Educational Data Mining 1 INTRODUCTION For the last 20 years, statistical analysis in education is a growing area that aims to offer high quality education that produces well-educated, skilled, mannered students according to needs and requirements of the dynamically growing market. The use of statistical analysis in education has grown in recent years for four primary reasons: a substantial increase in data quantity, improved data formats, advances in computing and increased development of tools available for analytics. Higher education institutions are not an exception and the use of analytics in education has grown in recent years for four primary reasons [1]. The available academic data can be collected, linked together and analysed to provide insights into student behaviours and identify patterns to potentially predict future outcomes. In this paper available data will be described as well as its potential use for the benefit of academic managers. The use of academic data for supporting tutoring action is where we will put the focus on. In recent years, the sophistication and ease of use of tools for data analytics make it possible for an increasing range of researchers to apply data mining methodology without needing extensive experience in computer programming. Many of these tools are adapted from the statistical data analysis for massive datafield. Higher education institutions have always operated in an information- rich landscape, generating and collecting vast amounts of data each day. A coarse classification of the types of data that higher education institutions deal with every day is: Student record data, Staff data, Admissions and applications data, Financial data, Alumni data, Course data, Facilities data, etc. Although the SPEET project goal is very clear (i.e. determine and categorize different profiles for engineering students across Europe), the approach to achieve student profiles in such a situation raises several questions and problems arising from the difficulty of the challenge assumed by the project partners, namely • the official data reported by universities are quantitative/numerical. The social context of the student is not investigated because of the fact that it is related with the education level of the environment he lives with, health habits and financial support. • the phenomenon of dropout from university studies has multiple causes which can be grouped at least into two major categories of factors: internal factors related to the student’s personality and her/his level of bio-psycho-social development and external factors related to the socioeconomic, cultural and educational environment in which the student lives.