Learning Profiles to Assess Educational Prediction Systems

Distance learning institutions record a high failure and dropout rate every year. This phenomenon is due to several reasons such as the total autonomy of learners lack regular monitoring. Therefore, education stakeholders need system which enables them prediction at-risk learners. solution commonly adopted in state art. However, its evaluation not generic does take into account diversity In this paper, we propose complete methodology objective more detailed proposed educational system. process aims ensure good performances system, regardless profiles. The combines both identification personas existing context according it. To meet challenge, used real dataset k-12 enrolled french distance institution.