Abstract
Predicting academic performance requires utilization of student related data and the accurate identification of the key issues regarding such data can enhance the prediction process. In this paper, we proposed a bootstrapped resampling approach for predicting the academic performance of university students using probabilistic modeling taking into consideration the bias issue of educational datasets. We include in this investigation students’ data at admission level, Year 1 and Year 2, respectively. For the purpose of modeling academic performance, we first address the imbalanced time series of educational datasets with a resampling method using bootstrap aggregating (bagging). We then ascertain the Bayesian network structure from the resampled dataset to compare the efficiency of our proposed approach with the original data approach. Hence, one interesting outcome was that of learning and testing the Bayesian model from the bootstrapped time series data. The prediction results were improved dramatically, especially for the minority class, which was for identifying the high risk of failing students.
Keywords
Supported by the Intelligent Data Analysis Research Laboratory, Brunel University London, United Kingdom.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
The Higher Education Statistics Agency (HESA) Website, HE student enrolments by level of study. https://www.hesa.ac.uk/data-and-analysis/sfr247/figure-3. Accessed 30 Jan 2019
Romero, C., López, M.I., Luna, J.M., Ventura, S.: Predicting students final performance from participation in on-line discussion forums. Comput. Educ. 68, 458–472 (2013)
Bhardwaj, B.K. and Pal, S.: Data mining: a prediction for performance improvement using classification. arXiv preprint arXiv:1201.3418 (2012)
Araque, F., Roldán, C., Salguero, A.: Factors influencing university drop out rates. Comput. Educ. 53(3), 563–574 (2009)
Seffrin, H.M., Rubi, G.L. Jaques, P.A.: A dynamic bayesian network for inference of learners’ algebraic knowledge. In: Proceedings of the 29th Annual ACM Symposium on Applied Computing, pp. 235–240. ACM (2014)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Elsevier (2014)
Witten, I.H., Frank, E., Hall, M.A., Pal, C.J.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, Burlington (2016)
Kabakchieva, D.: Predicting student performance by using data mining methods for classification. Cybern. Inf. Technol. 13(1), 61–72 (2013)
Kaur, G., Singh, W.: Prediction of student performance using weka tool. Int. J. Eng. Sci. 17, 8–16 (2016)
GarcÍa, P., Amandi, A., Schiaffino, S., Campo, M.: Evaluating Bayesian networks’ precision for detecting students’ learning styles. Comput, Educ. 49(3), 794–808 (2007)
Carmona, C., Castillo, G., Millán, E.: Designing a dynamic bayesian network for modeling students’ learning styles. In: 2008 Eighth IEEE International Conference on Advanced Learning Technologies, pp. 346–350 (2008)
Kaur, P., Singh, M., Josan, G.S.: Classification and prediction based data mining algorithms to predict slow learners in education sector. Procedia Comput. Sci. 57, 500–508 (2015)
Beal, C., Cohen, P.: Comparing apples and oranges: computational methods for evaluating student and group learning histories in intelligent tutoring systems. In: Proceedings of the 12th International Conference on Artificial Intelligence in Education, pp. 555–562 (2005)
McLaren, B.M., Koedinger, K.R., Schneider, M., Harrer, A., Bollen, L.: Bootstrapping novice data: semi-automated tutor authoring using student log files. In: Proceedings of Workshop on Analyzing Student-Tutor Interaction Logs to Improve Educational Outcomes, Proceedings of the 7th International Conference on ITS-2004: Intelligent Tutoring Systems (2004)
Feng, M., Beck, J.E., Heffernan, N.T.: Using Learning Decomposition and Bootstrapping with Randomization to Compare the Impact of Different Educational Interventions on Learning. International Working Group on Educational Data Mining (2009)
Pfannkuch, M., Forbes, S., Harraway, J., Budgett, S., Wild, C.: Bootstrapping students’ understanding of statistical inference. Summary research report for the Teaching and Learning Research Initiative (2013)
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Moniz, N., Branco, P. and Torgo, L.: Resampling strategies for imbalanced time series. In: 2016 IEEE International Conference Data Science and Advanced Analytics (DSAA), pp. 282–291. IEEE (2016)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newslett. 11(1), 10–18 (2009)
Druzdzel, M.J.: GeNIe: a development environment for graphical decision-theoretic models (1999)
Moon, T.K.: The expectation-maximization algorithm. IEEE SIgnal Process. Mag. 13(6), 47–60 (1996)
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 9, 1263–1284 (2008)
Acknowledgment
This work was partially funded through an internal Brunel Student Assessment and Retention grant (STARS Project).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Al-Luhaybi, M., Yousefi, L., Swift, S., Counsell, S., Tucker, A. (2019). Predicting Academic Performance: A Bootstrapping Approach for Learning Dynamic Bayesian Networks. In: Isotani, S., Millán, E., Ogan, A., Hastings, P., McLaren, B., Luckin, R. (eds) Artificial Intelligence in Education. AIED 2019. Lecture Notes in Computer Science(), vol 11625. Springer, Cham. https://doi.org/10.1007/978-3-030-23204-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-23204-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-23203-0
Online ISBN: 978-3-030-23204-7
eBook Packages: Computer ScienceComputer Science (R0)