Abstract:

This paper presents the first findings and products developed within the European ERASMUS+ project SPEET (Student Profile for Enhancing Engineering Tutoring). This project emerges from the potential synergy among a) the huge amount of academic data actually existing at the academic departments of faculties and schools, and b) the maturity of data science in order to provide algorithms and tools to analyse and extract information from what is more commonly referred to Big Data. A rich picture can be extracted from this data if conveniently processed. The main purpose of this project was to apply data mining algorithms to process this data in order to extract information about and to identify student performance characteristics.

The final goal of the project has been the development of an IT tool accessible to higher education institutions that will allow to upload and interactively analyse the correlations, relationships, clusters and groupings that can be extracted from the provided academic data. In addition, to fit a regression model in order to statistically get a prediction of the risk for a particular student to drop-out. In fact, drop-out is being more and more considered a central problem in higher education institutions. How to detect if one student is at risk of drop-out and, therefore, being able to introduce preventive actions may be of valuable help. Within the context of this project, we do not enter into the analysis of the best actions to be conducted to ensure the student finally accomplishes to finish the studies.

On the basis of the described scenario, this paper presents the a web based tool that may be of interest to anyone that aims for a direct work with their academic data.

Three basic kind of analysis are provided:
* Performance analysis algorithms: student performance analysis on the basis of categorical and/or performance data; performance for upcoming semesters on the basis of initial information; for explanatory analysis, etc
* Drop-out prediction algorithms: drop-out prediction on the basis of selected categorical information and first semester grades. A statistical model is elaborated that provides a quantitative evaluation of the student being at risk of drop-out.
* Visualization tools: for visual inspection of the pre-existing data relationships. Dimensional reduction and histogram techniques are applied to project the data on appropriate dimensions suitable for analysis. The tool provides a complete interactive, on-the-fly

First of all academic data is conveniently divided into categorical and performance data of the student as it progresses on the semesters of the degree the student is enrolled on. The main idea is to be able to predict student information as soon as possible by joining the categorical data (static) and the semesters performance (dynamic).

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, New Experiences for the International Cooperation, Educational Data Mining.