@proceedings { title = {Early prediction and variable importance of certificate accomplishment in a MOOC}, author = {Ruipérez-Valiente, José A. and Cobos, Ruth and Muñoz-Merino, Pedro J. and Andujar, Álvaro and Kloos, Carlos Delgado}, editor = {Kloos, Carlos Delgado and Jermann, Patrick and Pérez-Sanagustín, Mar and Seaton, Daniel T. and White, Su}, abstract = {The emergence of MOOCs (Massive Open Online Courses) makes available big amounts of data about students' interaction with online educational platforms. This allows for the possibility of making predictions about future learning outcomes of students based on these interactions. The prediction of certificate accomplishment can enable the early detection of students at risk, in order to perform interventions before it is too late. This study applies different machine learning techniques to predict which students are going to get a certificate during different timeframes. The purpose is to be able to analyze how the quality metrics change when the models have more data available. From the four machine learning techniques applied finally we choose a boosted trees model which provides stability in the prediction over the weeks with good quality metrics. We determine the variables that are most important for the prediction and how they change during the weeks of the course.}, year = {2017}, month = {05/2017}, publisher = {Springer International Publishing}, edition = {1}, volume = {10254}, pages = {263-272}, address = {Madrid}, country = {Spain}, doi = {https://doi.org/10.1007/978-3-319-59044-8_31}, url = {https://link.springer.com/chapter/10.1007/978-3-319-59044-8_31}, isbn = {978-3-319-59044-8}, refereed = {yes}, keywords = {educational data mining, learning analytics, machine learning, MOOCs, prediction}, }