Prediction of a student’s performance is one of the oldest and most popular applications of data mining in education, and different techniques and models have been applied. Patterns that are discovered by data mining methods from educational data will be used to enhance decision making in terms of identifying students at risk, decreasing student drop-out rate, increasing student’s success, and increasing student’s learning outcome.  These aspects need to be looked into very closely so that the application of data mining technique in the educational field produces a promising result. The primary goal of using data mining methods for the CRITON project is to develop a prediction model for the overall performance of the students in a selected course using their performance in prior courses and not only as predictor parameters.The objective of prediction is to estimate the unknown value of a variable that describes the student. In education the values normally predicted are performance, knowledge, score or mark. In the frame of CRITON project important indicators apart from grades will be emerged, which will play significant role in prediction of a student’s success or failure.

The CRITON platform (criton-platform.eu) will be a web based platform including a predictive system targeting to teachers and tutors in order to predict e-learners’ progress on time, and a social networking tool targeting to e-learners in order to facilitate learning communities to improve their potentials by developing their abilities and sharing knowledge.

The CRITON prediction system will be targeted to

• e-learners,
• tutors and
• educational organizations of different levels (secondary education, tertiary education, vocational training, and lifelong learning).

Here you can see the CRITON platform video

The CRITON predictive system proposed method is the following.