Abstract: This Talk is about predicting or classifying student’s performance starting from student’s usage/interaction data with learning environments. This is one of the most important tasks in Educational Data Mining (EDM) and Learning Analytics (LA) research communities. The first part of the talk describes the original paper presented in EDM’08 in Montreal as full paper. It compares different data mining algorithms provided by Keel DM software for classifying students based on both students’ usage data in 7 Moodle courses and the final marks obtained in the corresponding Cordoba University exams. The second part of the talk describes new research lines and improvements from 2008 to the present (2021): other DM tools/software and frameworks, other classification methods/algorithms, meta-learning for parameter tuning/algorithm selection, other evaluation metrics and statistical tests, the Baker LAP criteria, early warning prediction and more data from Multisource, Multimodal and Smart learning.

Bio: Cristóbal Romero is Full Professor at the University of Córdoba in Spain and member of KDIS (Knowledge Discovery and Intelligent Systems) research group and Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI). His main research interests are the application of data mining/learning analytics and artificial intelligence techniques to educational data/environment/domain. He has published more than 150 papers in books, journals and conferences, 50 of which have been published in Thomson-Reuters Impact Factor (IF) journals and some of them are important EDM (Educational Data Mining) surveys/reviews. He was also the co-editor of several special issues and two books regarding EDM specific topics. He was a founding officers of the international EDM society, associate editor of the IEEE Transaction on Learning Technologies journal and he has served in the program committee of a great number of international conferences about education, personalization artificial intelligence and data mining.