Early dropout prediction in moocs through supervised learning and hyperparameter optimization

Theodor Panagiotakopoulos, Sotiris Kotsiantis, Georgios Kostopoulos, Omiros Iatrellis, Achilles Kameas

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Over recent years, massive open online courses (MOOCs) have gained increasing popularity in the field of online education. Students with different needs and learning specificities are able to attend a wide range of specialized online courses offered by universities and educational institutions. As a result, large amounts of data regarding students’ demographic characteristics, activity patterns, and learning performances are generated and stored in institutional repositories on a daily basis. Unfortunately, a key issue in MOOCs is low completion rates, which directly affect student success. Therefore, it is of utmost importance for educational institutions and faculty members to find more effective practices and reduce non-completer ratios. In this context, the main purpose of the present study is to employ a plethora of state-of-the-art supervised machine learning algorithms for predicting student dropout in a MOOC for smart city professionals at an early stage. The experimental results show that accuracy exceeds 96% based on data collected during the first week of the course, thus enabling effective intervention strategies and support actions.

Original languageEnglish
Article number1701
JournalElectronics (Switzerland)
Issue number14
Publication statusPublished - 2 Jul 2021


  • Classification models
  • Completion rates
  • Dropout
  • Early prediction
  • MOOCs
  • Smart cities
  • Supervised learning


Dive into the research topics of 'Early dropout prediction in moocs through supervised learning and hyperparameter optimization'. Together they form a unique fingerprint.

Cite this