Statistical and Machine Learning Approach for Robust Assessment Modelling of Out-of-School Children Rate: Global Perspective

Full Text (PDF, 1323KB), PP.1-14

Views: 0 Downloads: 0


Edith Edimo Joseph 1,* Joseph Isabona 2 Sunday Dare 1 Odaro Osayande 3 Okiemute Roberts Omasheye 4

1. Department of Educational Psychology, University of KwaZulu-Natal, Edgewood Campus, South Africa

2. Department of Physics, Federal University Lokoja, Lokoja, Kogi State, Nigeria

3. Centre for Learning Resources, Covenant University, Ota, Ogun State, Nigeria

4. Delta State College of Education, Mosogar, Nigeria

* Corresponding author.


Received: 14 Nov. 2022 / Revised: 4 Jan. 2023 / Accepted: 11 Mar. 2023 / Published: 8 Jun. 2023

Index Terms

Global Perspective, LS-SVM, Out-of-School Children, SVM, UNESCO


The negative impact of out-of-school students' problems at the basic and high-school levels is always very weighty on the affected individuals, parents, and society at large. Owing to the weighty negative consequences, policymakers, different government agencies, educators and researchers have long been looking for how to effectively study and forecast the trends as a means of offering a concrete solution to the problem. This paper develops a better hybrid machine learning method, which combines the least square and support vector machine (LS-SVM) model for robust prediction improvement of out-of-school children trend patterns. Particularly, while other previous works only engaged some regional and few samples of out-of-school datasets, this paper focused on long-ranged global out-of-school datasets, collated by UNESCO between 1975- 2020. The proposed hybrid method exhibits the optimal precision accuracies with the LS-SVM model in comparison with ones made using the ordinary SVM model. The precision performance of both LS-SVM and SVM was quantified and a lower NRMSE value is preferred. From the results, the LS-SVM attained lower error values of 0.0164, 0.0221, 0.0268, 0.0209, 0.0158, 0.0201, 0.0147 and 0.0095 0.0188, compared to the SVM model that attained higher NRMSE values of 0.041, ,0.0628, 0.0381, 0.0490, 0.0501, 0.0493, 0.0514, 0.0617 and 0.0646, respectively. By engaging the MAPE indicator, which expresses the mean disconnection between the sourced and predicted values of the out-of-school data. By means of the MAPE, LS-SVM attained lower error values of 0.51, 1.88, 0.82, 2.38, 0.62, 2.55, 0.60, 0.60, 1.63 while SVM attained 1.83, 7.39, 1.79 7.01, 2.43, 8.79, 2.58, 4.13, 6.18. This implies that the LS-SVM model has better precision performance than the SVM model. The results attained in this work can serve as an excellent guide on how to explore hybrid machine-learning techniques to effectively study and predict out-of-school students among researchers and educators.

Cite This Paper

Edith Edimo Joseph, Joseph Isabona, Sunday Dare, Odaro Osayande, Okiemute Roberts Omasheye, "Statistical and Machine Learning Approach for Robust Assessment Modelling of Out-of-School Children Rate: Global Perspective", International Journal of Information Technology and Computer Science(IJITCS), Vol.15, No.3, pp.1-14, 2023. DOI:10.5815/ijitcs.2023.03.01


[1]UNESCO, 2022. UNESCO Institute of Statistics Data Centre:
[2]UNICEF and its Works for Children in West and Central Africa, https:/
[3]J. M. David and K. Balakrishnan, Prediction of Learning Disabilities in School-Age Children using SVM and Decision Tree, International Journal of Computer Science and Information Technologies, Vol. 2 (2), pp.829-835.
[4]Y.N. Mnyawami, H.H. Maziku and J.C. Mushi (2022) Enhanced Model for Predicting Student Dropouts in Developing Countries Using Automated Machine Learning Approach: A Case of Tanzanian’s Secondary Schools, Applied Artificial Intelligence, 36:1, 2071406, DOI: 10.1080/08839514.2022.2071406
[5]High-School Dropout Prediction using Machine Learning: A Danish Large-scale Study. ESANN 2015 Proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, April 22-24, Bruges, Belgium.
[6]H. Said, 2020. Developing Dropout Predictive System for Secondary Schools, By Using Classification Algorithm: A Case Study of Tabora Region. Dodoma City: University of Dodoma.
[7]S. Chakraborty and A. Ghoshal, Prediction and Analysis of Dropout Secondary Students in India Using Machine Learning Classification Algorithms, Abstracts of 1st International Conference on Machine Intelligence and System Sciences, MISS-2021),1–2 November 2021, Indian.
[8]S. Lee and J.Y. Chung, The Machine Learning-Based Dropout Early Warning System for Improving the Performance of Dropout Prediction. Appl. Sci. 2019, 9, 3093.
[9]A. O. Ameen1, M. A. Alarape, K. S. Adewole, Students’ Academic Performance, and Dropout Predictions: A Review, Malaysian Journal of Computing, 4 (2): 278-303, 2019.
[10]Dockery, D. J. (2012). School Dropout Indicators, Trends, and Interventions for School Counselors Donna J. Dockery Virginia Commonwealth University.
[11]M. Neema, Data Driven Approach for Predicting Student dropout in Secondary Schools, Ph.D. Thesis, The Nelson Mandela African Institution of Science and Technology, published in
[12]S. T. Ahmed, R. S. Al-hamdani, and M. S. Croock, Studying of Educational Data Mining Techniques, International Journal of Advanced Research in Science, Engineering and Technology, Vol. 5, Issue 5, pp.5743-5750. May 2018.
[13]Mukesh Kumar, A.J. Singh, Disha Handa,"Literature Survey on Educational Dropout Prediction", International Journal of Education and Management Engineering(IJEME), Vol.7, No.2, pp.8-19, 2017.DOI: 10.5815/ijeme.2017.02.02
[14]D.E Moreira da Silva.; E.J Solteiro Pires, A. Reis, P.B. de Moura Oliveira, and J..Barroso, Forecasting Students Dropout: A UTAD University Study. Future Internet 2022, 14, 76.
[15]R. Kenneth Koedinger et al. presented “Data mining and education”. WIREs Cogn Sci 2015. doi:10.1002/wcs.1350
[16]Laura Calvet Linan et al presented “Educational Data Mining and Learning Analytics: differences, similarities, and time evolution”. Universities and Knowledge Society Journal, 12(3). pp. 98-112. doi:
[17]Ebhota, V.C, Isabona, J, and Srivastava, V.M. (2019), Environment-Adaptation Based Hybrid Neural Network Predictor for Signal Propagation Loss Prediction in Cluttered and Open Urban Microcells, Wireless Personal Communications, Vol. 104 (3), pp. 935–948.
[18]V.C. Ebhota, J. Isabona, and V.M. Srivastava, (2019), Investigation and Comparison of Generalization Ability of Multi-Layer Perceptron and Radial Basis Function Artificial Neural Networks for Signal Power Loss Prediction, International Journal on Communications Antenna and Propagation, Vol. 9 (1), pp. 43-54.
[19]V.C. Ebhota, J. Isabona, and V.M.Srivastava (2019), Effect of Learning Rate on GRNN and MLP for the Prediction of Signal Power Loss in Microcell Sub-Urban Environment, International Journal on Communications Antenna and Propagation, Vol. 9 (1), pp. 36-45.
[20]J. Isabona, (2021). Joint Statistical and Machine Learning Approach for Practical Data Driven Assessment of User Throughput Quality in Microcellular Radio Networks, Wireless Personal Communication (Springer), vol, 119, pp. 1661–1680.
[21]Joseph Isabona, Divine O. Ojuh, "Application of Levenberg-Marguardt Algorithm for Prime Radio Propagation Wave Attenuation Modelling in Typical Urban, Suburban and Rural Terrains", International Journal of Intelligent Systems and Applications(IJISA), Vol.13, No.3, pp.35-42, 2021. DOI: 10.5815/ijisa.2021.03.04
[22]J. Isabona, (2020), Wavelet Generalized Regression Neural Network Approach for Robust Field Strength Prediction in Open and Shadow Urban Microcells, Wireless Personal Communications, Vol. 114 (3), pp.3635–3653.
[23]Odesanya Ituabhor, Joseph Isabona, Jangfa T. zhimwang, Ikechi Risi, "Cascade Forward Neural Networks-based Adaptive Model for Real-time Adaptive Learning of Stochastic Signal Power Datasets", International Journal of Computer Network and Information Security(IJCNIS), Vol.14, No.3, pp.63-74, 2022. DOI: 10.5815/ijcnis.2022.03.05
[24]K. Obahiagbon, and J. Isabona, (2018), Generalized Regression Neural Network: an Alternative Approach for Reliable Prognostic Analysis of Spatial Signal Power Loss in Cellular Broadband Networks, International Journal of Advanced Research in Physical Science, vol. 5(10): 35-42.
[25]Joseph Isabona, Divine O. Ojuh," Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates ", International Journal of Mathematical Sciences and Computing(IJMSC), Vol.7, No.2, pp. 14-23, 2021. DOI: 10.5815/ijmsc.2021.02.02
[26]J. Isabona Joseph, O. Ituabhor and D.O. Ojuh.O.Divine, Poynting Vector Joint with Weighted Least Square Regression Technique for Optimal Electric Field Strength Modelling, International Journal of Computing and Digital Systems, vol.12, No.1, 517-527 (Dec-2022).
[27]S. Hassan, Abbas Karamodin, Alireza Entezami, A new iterative model updating technique based on least squares minimal residual method using measured modal data, Applied Mathematical Modelling, Vol. 40, Issues 23–24, 10323-10341, 2016.
[28]O.R. Omasheye, S. Azi, J. Isabona, A.L. Imoize, C-T. Li, C-C and C-C. Lee C. Joint Random Forest and Particle Swarm Optimization for Predictive Pathloss Modeling of Wireless Signals from Cellular Networks. Future Internet; vol.14(12), 2022:373.