Education and Information Technologies

, Volume 24, Issue 6, pp 3591–3618 | Cite as

A predictive approach based on efficient feature selection and learning algorithms’ competition: Case of learners’ dropout in MOOCs

  • Mourdi YoussefEmail author
  • Sadgal Mohammed
  • El Kabtane Hamada
  • Berrada Fathi Wafaa


MOOCs are becoming more and more involved in the pedagogical experimentation of universities whose infrastructure does not respond to the growing mass of learners. These universities aim to complete their initial training with distance learning courses. Unfortunately, the efforts made to succeed in this pedagogical model are facing a dropout rate of enrolled learners reaching 90% in some cases. This makes the coaching, the group formation of learners, and the instructor/learner interaction challenging. It is within this context that this research aims to propose a predictive model allowing to classify the MOOCs learners into three classes: the learners at risk of dropping out, those who are likely to fail and those who are on the road to success. An automatic determination of relevant attributes for analysis, classification, interpretation and prediction from MOOC learners data, will allow instructors to streamline interventions for each class. To meet this purpose, we present an approach based on feature selection methods and ensemble machine learning algorithms. The proposed model was tested on a dataset of over 5,500 learners in two Stanford University MOOCs courses. In order to attest its performance (98.6%), a comparison was carried out based on several performance measures.


Dropout Distance education Feature selection Algorithms competition Educational datamining MOOC 



This research was done through Stanford University’s Advanced Research Center on Online Learning (CAROL), which we thank immensely for all the facilities they provided for us. We also wish to express our full gratitude to Ms. Kathy Mirzaei for her responsiveness as well as her collaboration. We wish to warmly thank Mr. Mitchell Stevens, Director of Digital Research and Planning, as well as all the CAROL commission for the trust they have given us.


  1. Al-Shabandar, R., Hussain, A., Laws, A., Keight, R., Lunn, J., Radi, N. (2017). Machine learning approaches to predict learning outcomes in Massive open online courses. Int. Jt. Conf. Neural Networks (pp. 713—720).Google Scholar
  2. Alonso-betanzos, A. (2007). Filter methods for feature selection. A comparative study. Proc. International Conference on Intelligent Data Engineering and Automated Learning (pp. 178—187). UK, Birmingham.Google Scholar
  3. Alves, A. (2017). Stacking machine learning classifiers to identify Higgs bosons at the LHC. Journal of Instrumentation, 12, 1–19.CrossRefGoogle Scholar
  4. Armbrust, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J., Ghodsi, A., et al. (2015). Spark SQL: Relational Data Processing in Spark. Proceedings of International Conference Management Data (pp. 1383—1394). Australia, Melbourne.Google Scholar
  5. Burgos, C., Campanario, M.L., de la Pena, D., Lara, J.A., Lizcano, D., Martinez, M.A. (2018). Data mining for modeling students’ performance: A tutoring action plan to prevent academic dropout. Computer Electrical Engineering, 66, 541–556.CrossRefGoogle Scholar
  6. Chaplot, D.S., Rhim, E., Kim, J. (2015). Predicting student attrition in MOOCs using sentiment analysis and neural networks. Proc. CEUR Workshop, 1432, 7–12.Google Scholar
  7. Choudhury, S., & Bhowal, A. (2015). Comparative analysis of machine learning algorithms along with classifiers for network intrusion detection. Proceedings of International Conference in Smart Technology of Management Computer Communication Controlling Energy Material (pp. 89—95). India, Chennai.Google Scholar
  8. Cross, S. (2013). Evaluation of the OLDS MOOC curriculum design course: participant perspectives expectations and experiences. OLDS MOOC Proj. Google Scholar
  9. Crossley, S., Paquette, L., Dascalu, M., McNamara, D.S., Baker, R.S. (2016). Combining click-stream data with NLP tools to better understand MOOC completion. Proc. Sixth Int. Conf. Learn. Anal. Knowl. (pp. 6—14). UK, Edinburgh.Google Scholar
  10. Dinakar, K., Weinstein, E., Lieberman, H., Selman, R. (2014). Stacked Generalization Learning to Analyze Teenage Distress. Proceedings of the Eighth International AAAI Conference on Weblogs and Social Media (pp. 81—90). USA, Michigan.Google Scholar
  11. Fei, M., & Yeung, D.-Y. (2018). Temporal Models for Predicting Student Dropout in Massive Open Online Courses. IEEE International Conference on Data Mining Working (pp. 256—263). Singapore.Google Scholar
  12. Gitinabard, N., Khoshnevisan, F., Lynch, C.F., Wang, E.Y. (2018). Your Actions or Your Associates? Predicting Certification and Dropout in MOOCs with Behavioral and Social Features. Proc. 11th International Conference on Educational Data Mining. Buffalo NY: In Press.Google Scholar
  13. Healey, S.P., Cohen, W.B., Yang, Z., Brewer, C.K., Brooks, E.B., Gorelick, N., Hernandez, A.J., Huang, C., Hughes, M.J., Kennedy, R.E., et al. (2018). MApping forest change using stacked generalization: An ensemble approach. Remote Sensing Environment, 204, 717–728.CrossRefGoogle Scholar
  14. Jindal, P., & Kumar, D. (2019). A Review on Dimensionality Reduction Techniques, International Journal Pattern Recognition of Artificial Intelligence. In Press.Google Scholar
  15. Jović, A., Brkić, K., Bogunović, N. (2015). A review of feature selection methods with applications Proceedings of 38th International Convenience of Information Communication Technology Electronic Microelectronics (pp. 1200—1205). Croatia, Opatija.Google Scholar
  16. Kabir, A., Ruiz, C., Alvarez, S.A. (2014). Regression, Classification and Ensemble Machine Learning Approaches to Forecasting Clinical Outcomes in Ischemic Stroke. Biomedical Engineering Systems and Technologies, 452, 376–402.Google Scholar
  17. Karegowda, A.G., Manjunath, A.S., Jayaram, M.A. (2010). Feature Subset Selection Problem using Wrapper Approach in Supervised Learning. International of Journal Computer Application, 1, 13–17.CrossRefGoogle Scholar
  18. Kloft, M., Stiehler, F., Zheng, Z., Pinkwart, N. (2014). Predicting MOOC Dropout over Weeks Using Machine Learning Methods. Proc. Conf. Empir. Methods Nat. Lang. Process. (pp. 60—65).Google Scholar
  19. Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R.P., Tang, J., Liu, H. (2018). Feature selection: a data perspective, ACM Computer Survey, 50.CrossRefGoogle Scholar
  20. Liyanagunawardena, T.R., Parslow, P., Williams, S.A. (2014). Dropout: MOOC participants’ perspective. Proceedings of European MOOC Stakehold (pp. 95–100). Switzerland: Summit.Google Scholar
  21. Martínez-España, R., Bueno-Crespo, A., Timón, I., Soto, J., Muñoz, A., Cecilia, J.M. (2018). Air-pollution prediction in smart cities through machine learning methods: A case of study in Murcia. Spain, Journal University of Computer Science, 24, 261–276.Google Scholar
  22. Meng, X., Bradley, J., Yavuz, B., Sparks, E., Venkataraman, S., Liu, D., Freeman, J., Tsai, D.B., Amde, M., Owen, S. (2016). Others MLlib: Machine Learning in Apache Spark. Journal of Machine Learning Research, 17, 1235–1241.zbMATHGoogle Scholar
  23. Naghibi, S.A., Ahmadi, K., Daneshi, A. (2017). Application of Support Vector Machine, Random Forest, and Genetic Algorithm Optimized Random Forest Models in Groundwater Potential Mapping. Water Resources Management, 31, 2761–2775.CrossRefGoogle Scholar
  24. Nagi, S., & Bhattacharyya, D.K. (2013). Classification of microarray cancer data using ensemble approach. Network Modelling Analysis of Health Informatics Bioinforma, 2, 159–173.CrossRefGoogle Scholar
  25. Onah, D.F., & Sinclair, J. (2014). Boyatt Dropout Rates of Massive Open Online Courses: Behavioural Patterns MOOC Dropout and Completion: Existing Evaluations, Proceedings of 6th International Conference on Education (pp. 1–10). Spain: New Learn. Technol.Google Scholar
  26. Panthong, R., & Srivihok, A. (2015). Wrapper Feature Subset Selection for Dimension Reduction Based on Ensemble Learning Algorithm. Procedia Computer Science, 72, 162–169.CrossRefGoogle Scholar
  27. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2012). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830.MathSciNetzbMATHGoogle Scholar
  28. Prieto, L.P., Rodríguez-Triana, M.J., Kusmin, M., Laanpere, M. (2017). Smart school multimodal dataset and challenges. Proceedings of CEUR Workshop, 1828, 53–59.Google Scholar
  29. Qi, Q., Liu, Y., Wu, F., Yan Xi., Wu, N. (2018). Temporal Models for Personalized Grade Prediction in Massive Open Online Courses. Proceedings of ACM Turing Celebration Conference (pp. 67—72).Google Scholar
  30. Qiu, L., Liu, Y., Hu, Q., Liu, Y. (2018a). Student dropout prediction in massive open online courses by convolutional neural networks. bSoft Computer, 22, 1–15.Google Scholar
  31. Qiu, L., Liu, Y., Liu, Y. (2018b). An integrated framework with feature selection for dropout prediction in massive open online courses. IEEE Access, 6, 71474–71484.CrossRefGoogle Scholar
  32. Ren, Y., Zhang, L., Suganthan, P.N. (2016). Ensemble Classification and Regression-Recent Developments, Applications and Future Directions. IEEE Computer of Intelligence Magazine, 11, 41–53.CrossRefGoogle Scholar
  33. Salcedo-Sanz, S., Cornejo-Bueno, L., Prieto, L., Paredes, D., García-Herrera, R. (2018). Feature selection in machine learning prediction systems for renewable energy applications. Renewable and Sustainable Energy Reviews, 90, 728–741.CrossRefGoogle Scholar
  34. Sanchez-Gordon, S., & Luján-Mora, S. (2016). How could MOOCs become accessible? The case of edX and the future of inclusive online learning. Journal University of Computer Science, 22, 55–81.Google Scholar
  35. Sikora, R., & Al-Laymoun, O. (2014). A Modified Stacking Ensemble Machine Learning Algorithm Using Genetic Algorithms. Handbook of Research on Organizational Transformations through Big Data Analytics, 23, 43–53.Google Scholar
  36. Sinha, T., Jermann, P., Li, N., Dillenbourg, P. (2014). Your click decides your fate: Inferring Information Processing and Attrition Behavior from MOOC Video Clickstream Interactions. Proceedings of Conference Empirial Methods Nat. Lang. Process. (pp. 6—14).Google Scholar
  37. Talavera, L. (2005). An Evaluation of Filter and Wrapper Methods for Feature Selection in Categorical Clustering. Proceedings of International Symposium on Intelligent Data Analysis (pp. 440—451). Spain, Madrid.zbMATHGoogle Scholar
  38. Tang, C., Ouyang, Y., Rong, W., Zhang, J., Xiong, Z. (2018). Time series model for predicting dropout in massive open online courses, Proc. International conference on artificial intelligence in education (pp. 353–357). UK.Google Scholar
  39. Vitiello, M., Walk, S., Helic, D., Chang, V., Gütl, C. (2018). User behavioral patterns and early dropouts detection: Improved users profiling through analysis of successive offering of MOOC. Journal University of Computer Science, 24, 1131–1150.Google Scholar
  40. White, T. (2012). Hadoop: The definitive guide. USA: O’Reilly Media, Inc.Google Scholar
  41. Witten, I. (2016). Data mining: Practical machine learning tools and techniques. Burlington: MorganKaufmann.zbMATHGoogle Scholar
  42. Xing, W., Chen, X., Stein, J., Marcinkowski, M. (2016). Temporal predication of dropouts in MOOCs: Reaching the low hanging fruit through stacking generalization. Comput. Human Behav., 58, 119–129.CrossRefGoogle Scholar
  43. Xu, S., Lu, B., Baldea, M., Edgar, T.F., Nixon, M. (2018). An improved variable selection method for support vector regression in NIR spectral modeling. Journal Process Control, 67, 83–93.CrossRefGoogle Scholar
  44. Yang, D., Sinha, T., Adamson, D. (2016). ’Turn on, Tune in, Drop out’: Anticipating student dropouts in Massive Open Online Courses. Proc. NIPS Work. Data Driven Educ. (pp. 1—8).Google Scholar
  45. Yuan, L., & Powell, S. (2013). MOOCS and disruptive innovation: Implications for higher education. In-depth eLearning Papers, 33, 1–7.Google Scholar
  46. Zhu, Y., Xie, C., Wang, G.J., Yan, X.G. (2017). Comparison of individual, ensemble and integrated ensemble machine learning methods to predict China’s SME credit risk in supply chain finance. Neural Computer Applications, 28, 41–50.CrossRefGoogle Scholar
  47. Zitlau, R., Hoyle, B., Paech, K., Weller, J., Rau, M.M., Seitz, S. (2016). Stacking for machine learning redshifts applied to SDSS galaxies. Monthly Not. R. Astron. Soc., 460, 3152–3162.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science DepartementCADI AYYAD UniversityMarrakechMorocco

Personalised recommendations