Abstract
School dropout is a significant issue, especially in develo** countries due to high poverty levels and inadequate allocation of resources to education. This study applies Machine Learning to predict dropouts in the Lilongwe University of Agriculture and Natural Resources’ open and distance education system. Four supervised machine learning classifiers (Gaussian Naïve Bayes, Logistic Regression, K-Nearest Neighbour, and Random Forest) were assessed to find the best predictor for dropouts. Data imbalance was addressed using oversampling and undersampling techniques. Results showed that Random Forest performed the best with under-sampling. Hyperparameter optimization using grid and random search methods also improved performance, with Random Forest emerging as the best classifier. This study contributes to future research and enhances the existing literature. It is expected to improve student support services by proactively addressing at-risk students, reducing attrition rates.
Supported by LUANAR/MUBAS.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alice, K., Folorunso, O., Lateef, U.: Predicting students’ grade scores using training functions of artificial neural network. J. Nat. Sci. Eng. Technol. 14(February), 25–42 (2015)
Aulck, L., Velagapudi, N., Blumenstock, J., West, J.: Predicting Student Dropout in Higher Education (2016). http://arxiv.org/abs/1606.06364
Brossard, M., Diane, C., Michael, M.: The Education System in Malawi (2010). https://doi.org/10.1596/978-0-8213-8198-4
Chawinga, W.D., Zozie, P.A.: Increasing access to higher education through open and distance learning: empirical findings from Mzuzu University, Malawi. Int. Rev. Res. Open Distance Learn. 17(4), 1–20 (2016). https://doi.org/10.19173/irrodl.v17i4.2409
Chibambo, M., Wellman, K.: Are peerless e-resources any better tools for supporting students in open and distance learning environments than the more traditional tools? The case of Mzuzu University, Malawi. Res. World: J. Arts Sci. Commerce VIII(3), 126–138 (2017). https://doi.org/10.18843/rwjasc/v8i3/14
Janerose, Y.: School Feeding Programmes in Chimutu, Malawi: Opportunities, benefits and challenges. University of Fort Hare (2013). http://hdl.handle.net/20.500.11837/522
Lee, S., Chung, J.Y.: The machine learning-based dropout early warning system for improving the performance of dropout prediction. Appl. Sci. (Switzerland) 9(15) (2019). https://doi.org/10.3390/app9153093
Lottering, R., Hans, R., Lall, M.: A machine learning approach to identifying students at risk of dropout: a case study. Int. J. Adv. Comput. Sci. Appl. 11(10). https://doi.org/10.14569/ijacsa.2020.0111052
Ministry of Education: 2019 Malawi Education Statistics Report (2019)
Mduma, N., Kalegele, K., Machuve, D.: A survey of machine learning approaches and techniques for student dropout prediction. Data Sci. J. 18(1) (2019). https://doi.org/10.5334/dsj-2019-014
Mduma, N., Kalegele, K., Machuve, D.: Machine learning approach for reducing student’s dropout rates. Int. J. Adv. Comput. Res. 9(42), 156–169 (2019). https://doi.org/10.19101/ijacr.2018.839045
Mgala, M.: Investigating Prediction Modelling of Academic Performance for Students in Rural Schools in Kenya. University of Cape Town (2016). http://hdl.handle.net/11427/23463
Mzuza, M.K., Yudong, Y., Kapute, F.: Analysis of factors causing poor passing rates and high dropout rates among primary school girls in Malawi. World J. Educ. 4(1) (2014). https://doi.org/10.5430/wje.v4n1p48
Naunje, C.W.: ScholarWorks@UMass Amherst The Magnitude and Causes of Dropout in Malawi: A Study of Chiradzulu District (2014). https://scholarworks.umass.edu/cie_capstones/47
Pike, I., Grant, M.: Gifting Relationships and School Dropout in Rural Malawi: Examining Differences by Gender and Poverty Level (2019)
Ramphele, F.: Predicting grade progression within the Limpopo Education System. University of Cape Town (2018). http://hdl.handle.net/11427/30137
Stapel, M., Zheng, Z., Pinkwart, N.: An ensemble method to predict student performance in an online math learning environment. In: Proceedings of the 9th International Conference on Educational Data Mining. EregulDM 2016, pp. 231–238 (2016)
Umar, F., Ussiph, N.: Appraisal of the classification technique in data mining of student performance using j48 decision tree, K-nearest neighbor and multilayer perceptron algorithms. Int. J. Comput. Appl. 179(33), 39–46 (2018). https://doi.org/10.5120/ijca2018916751
Adam, S., Adom, D., Bediako, A.B.: The Major Factors That Influence Basic School Dropout in Rural Ghana: The Case of Asunafo South District in the Brong Ahafo Region of Ghana, vol. 7, no. 28. (2016). www.iiste.org
Gudeta O.: Factors Affecting Students’ Dropout in Secondary Schools of Wayu Tuka Woreda East Wollega Zone Oromya Regional State Department of Educational Planning and Management: College of Education and Behavioral Studies, Addis Ababa University Addis Ababa Ethiopia (2019)
Hurwitz, J., Kirsch, D.: Machine Learning IBM Limited Edition (2018). http://www.wiley.com/go/permissions
Kavetuna, J.: Formal Education Open Schooling (n.d.)
Mahoney, J.L.: School dropout. In: Bornstein, M.H. (ed.) The SAGE Encyclopedia of Lifespan Human Development, pp. 1889–1891. SAGE, Thousand Oaks (2018). https://www.researchgate.net/publication/326098844
Mantovani, R.G., Rossi, A.L.D., Alcobaça, E., Gertrudes, J.C., Junior, S.B., de Carvalho, A.C.P.D.L.F.: Rethinking default values: a low cost and efficient strategy to define hyperparameters. ar**v preprint ar**v:2008.00025 (2020)
Matache, C., Passerat, J., Kainz, B.: Efficient Design of Machine Learning Hyperparameter Optimizers. MEng Individual Project, pp. 17–18. Imperial College London (2019)
Tran, N., Schneider, J.G., Weber, I., Qin, A.K.: Hyper-parameter optimization in classification: to-do or not-to-do. Pattern Recogn. 103, 107245 (2020). https://doi.org/10.1016/j.patcog.2020.107245
Kumar, V.: Feature selection: a literature review. Smart Comput. Rev. 4 (2014). https://doi.org/10.6029/smartcr.2014.03.007
Kumar, G., Kumar, K.: An information theoretic approach for feature selection. Secur. Commun. Netw. 5, 178–185 (2012). https://doi.org/10.1002/sec.303
BolónCanedo, V., Remeseiro, B., Cancela, B.: Feature Selection for Big Visual Data: Overview and Challenges (2018). https://doi.org/10.1007/978-3-319-93000-8_16
Yokozeki, Y.: The causes, processes and consequences of student drop-out from Junior Secondary School (JSS) in Ghana: the case of Komenda-Edina-Eguafo-Abrem (K.E.E.A.) district (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Hara, M., Taylor, A., Gawanani, P. (2024). Predicting School Dropout in Malawi. In: Crawford, D., Foss, J., Lambert, N., Reed, M., Kriebel, J. (eds) Technology, Innovation, Entrepreneurship and Education. TIE 2023. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 575. Springer, Cham. https://doi.org/10.1007/978-3-031-59383-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-59383-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-59382-6
Online ISBN: 978-3-031-59383-3
eBook Packages: Computer ScienceComputer Science (R0)