This research has three main strands, as described below. Today, the fashionable term for this kind of research might be Learning Analytics.
One is on attempting to model the student populations, based on students' preferences, course precedence constraints and university policies. The results are published in technical reports (the most up-to-date of which can be found at http://arxiv.org/abs/cs/0701174) and in the following paper:
Th. Hadzilacos, D. Kalles, D. Koumanakos and V. Mitsionis. "A Prototype for Educational Planning Using Course Constraints to Simulate Student Populations", International Journal on Artificial Intelligence Tools, Vol. 18, Iss. 4, pp. 621-630, 2009.
Then, there is another one on exploring how one can use student performance data to derive success/failure models at exams.
Incidentally, these models also help explore the relationship between tutoring practices and student success as well as the organisational implications of tutoring practices.
The research is described in the following papers:
Th. Hadzilacos, D. Kalles, and C. Pierrakeas. ”On Developing and Communicating User Models for Distance Learning based on Assignment and Exam Data”, Intelligent Interactive Systems in Knowledge-based Environments, M. Virvou and L. Jain (eds), Springer, pp. 137-155, 2008.
D. Kalles, C. Pierrakeas and M. Xenos. "Intelligently Raising Academic Performance Alerts", 1st International Workshop on Combinations of Intelligent Methods and Applications (CIMA), 18th European Conference on Artificial Intelligence, pp. 37-42, Patras, Greece, July 2008.
D. Kalles and C. Pierrakeas. "Analyzing Student Performance in Distance Learning with Genetic Algorithms and Decision Trees", Applied Artificial Intelligence, Vol. 20, No. 8, pp. 655-674, 2006.
Th. Hadzilacos and D. Kalles. "On the Software Engineering Aspects of Educational Intelligence", 10th International Conference on Knowledge-Based Intelligent Information & Engineering Systems, Bournemouth, UK, October 2006.
D. Kalles and C. Pierrakeas. "Using Genetic Algorithms and Decision Trees for a posteriori Analysis and Evaluation of Tutoring Practices based on Student Failure Models", 3rd IFIP Conference on Artificial Intelligence Applications and Innovations, Athens, Greece, June 2006.
Th. Hadzilacos, D. Kalles, C. Pierrakeas and M. Xenos. "On Small Data Sets revealing Big Differences", Panhellenic Conference on Artificial Intelligence, Heraklion, Greece, 2006.
And, finally, there is another one how to develop empirical models to describe the maturity of online learning communities.
The research is described in the following papers:
E. Lotsari, V.S. Verykios, C.Panagiotakopoulos and D. Kalles. “A Learning Analytics Methodology for Student Profiling”, Panhellenic Conference on Artificial Intelligence, Heraklion, Greece, May, 2014.
D. Karaiskakis, D. Kalles, and Th. Hadzilacos. “Profiling Group Activity of Online Academic Workspaces: the Hellenic Open University case study”, International Journal of Web-based Learning and Teaching Technology, Vol. 3, No. 3, pp. 1 – 15, 2008.
Th. Hadzilacos, D. Karaiskakis and D. Kalles. “Tracking User Participation in a Large Scale Team Collaboration Environment”, Workshop on Technology Enhanced Learning – Communities of Practice, Hersonnisos, Greece, October 2006.