The initial main objective of the project was the development of an IT tool aimed at providing an automated analysis of student academic data as a service for higher education institutions. The project consortium managed to complete all the tasks and products agreed on in the early stage of application. The original project objectives have therefore been reached in time and form. Now, once the project is finished, the generated IT tool has the form of a web service accessible at https://speet.uab.cat. Also from this website, the other project outputs, identified as intellectual outputs, can be accessed. Major project achievements are reflected in the corresponding intellectual outputs and project formal activities. Intellectual Outputs (IOs) generated under this project implementation have been produced accordingly to its established planning. In all IOs, a text document has been generated. They took the form of a book series with main title “Data Mining tool for Academic Data Exploitation”, and published in open access with ISBN. In addition to this text document, additional material has been generated as part of IO2, IO3 and IO5. In these cases, computer source code for the implemented algorithms in a way such that code sharing is facilitated, has been provided for IO2 and IO3, whereas the final IT tool has been put into service as part of IO5. Whereas IO5 is the output aimed at a major impact and that better reflects the project development, because it constitutes the main output of the project. Being the other generated outputs, i.e., IO1, IO2, IO3 and IO4, studies on the different steps that conduct towards IO5, they have to be considered part of the wide study that this project has undertaken. Therefore, they have to be considered as different contributions on the overall problem of academic data analysis Major project achievements are reflected in the corresponding intellectual outputs and project formal activities. However, in addition to them, the project reached a series of side achievements that are worth to comment. Most of them are of intangible or qualitative nature and expressed at institutional level. Even qualitative, and perspective-related, from the partnership point of view they are very important as completely necessary for a shift of perspective related to the adoption of educational data mining solutions. • Institutional awareness of the academic data information system status. • Raising awareness about the importance of the tutoring action and the introduction of ITC tools on the tutor side. • Exploiting historical academic data has raised the need to deal with the ethical points related to student information usage. It has been verified by the participating institutions that the project has promoted institutional discussions on these sensible topics that, otherwise, are very unlikely to arise. Outputs from this project will allow now academic managers and tutors to enhance their activity. The project, therefore, opened a new perspective to tutoring systems based on accumulated experience that resides on students’ track records databases. This supporting IT for tutoring actions has been made possible with the tools that have been developed in this project.
This project goal 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 purpose of this project is to apply data mining algorithms to process this data in order to extract information about and to identify student profiles. An idea of the student profile we are referring to within the project scope is, for example: Students that finish degree on time, Students that are blocked on a certain set of subjects, Students that leave degree earlier, etc.With such classification that, of course, devise a more precise definition and categorization that will be established from the very beginning of the project the more usual student patterns will be depicted. Comparison among the different partner institutions will be done in order to establish correlations and get a more complete European-level picture. The main question that will be asked once these student profiles are determined is regarding once a new student gets enrolled, could we know as in advance as possible which profile this student obeys to? This would definitively help tutor this student providing data founded recommendations in order to avoid early leaving, increase motivation and better pass blocking subjects, etc.An IT tool is intended to be produced in order to help disseminate the study and allow other faculties and schools to conduct similar study. It is worth to stress that as far as the scope of this project is concerned, the study will concentrate on engineering students. This will help to delimit and better define / analyse the results. A rough outline of the project phases are outlines as:1.- Available data and a priori characterization of potential student profiles.2.- Pre-processing of data. First examples of processing outputs and database generation from partners3.- Data analysis at partner level. Interpretation of categories and profiles4.- Setting up the basis and definitions for an IT-based assistant tutoring system.5.- Prototyping the developed tools into a website based tool.