ICT Adoption, Human Development, and Productivity Change in Sub-Saharan Africa: Evidence from Random Forest and DEA-Malmquist Analysis

Refilwe Maidi; Ernest Mnkandla

doi:10.63158/journalisi.v8i5.1866

Authors

Refilwe Maidi University of South Africa
Ernest Mnkandla University of South Africa

DOI:

https://doi.org/10.63158/journalisi.v8i5.1866

Keywords:

ICT4D, ICT Adoption, Human Development, Life Expectancy, Adult Literacy, Sub-Saharan Africa, Random Forest, DEA-Malmquist Analysis

Abstract

Information and Communication Technologies (ICTs) are increasingly recognized as important enablers of human development through improved access to education, healthcare, and information. This study examined the association between ICT adoption, life expectancy, and literacy rates in 49 Sub-Saharan African countries. The study used panel data from 49 Sub-Saharan African countries for the period 2010 to 2022. Random Forest analysis was used to identify patterns and determine the ICT indicators most strongly associated with human development outcomes, while an online survey provided additional insights into ICT adoption. DEA-Malmquist analysis was applied to evaluate productivity growth and technological change over time. The results indicate that ICT adoption is positively associated with life expectancy and literacy rates. Internet penetration emerged as the most influential predictor in both models, accounting for approximately 89% of total feature importance. The DEA-Malmquist analysis revealed average productivity growth of 17.2%, driven mainly by technological change. These findings suggest that expanding access to digital technologies can support improvements in education and health outcomes. The study contributes to ICT4D research by combining Random Forest and DEA-Malmquist methods and provides evidence to inform digital inclusion policies that promote human development in Sub-Saharan Africa.

Downloads

Download data is not yet available.

References

[1] S. A. Asongu and S. Le Roux, “Enhancing ICT for inclusive human development in Sub-Saharan Africa,” Technol. Forecast. Soc. Change, vol. 118, pp. 44–54, 2017, doi: 10.1016/j.techfore.2017.01.026.

[2] Y. Kim and K. Crowston, “Technology adoption and use: Theory review for studying scientists’ continued use of cyber-infrastructure,” in Proc. ASIST Annu. Meeting, vol. 48, pp. 1–10, 2011, doi: 10.1002/meet.2011.14504801197.

[3] T. Oliveira and M. F. Martins, “Literature review of information technology adoption models at firm level,” Electron. J. Inf. Syst. Eval., vol. 14, no. 1, pp. 110–121, 2011.

[4] V. Venkatesh, M. G. Morris, G. B. Davis, and F. D. Davis, “User acceptance of information technology: Toward a unified view,” MIS Quart., vol. 27, no. 3, pp. 425–478, 2003, doi: 10.2307/30036540.

[5] J. Alzubi, A. Nayyar, and A. Kumar, “Machine learning from theory to algorithms: An overview,” J. Phys.: Conf. Ser., vol. 1142, no. 1, Art. no. 012012, 2018, doi: 10.1088/1742-6596/1142/1/012012.

[6] B. Mahesh, “Machine learning algorithms: A review,” Int. J. Sci. Res., vol. 9, no. 1, pp. 381–386, 2020, doi: 10.21275/ART20203995.

[7] A. L. Samuel, “Some studies in machine learning using the game of checkers,” IBM J. Res. Develop., vol. 3, no. 3, pp. 210–229, 1959, doi: 10.1147/rd.33.0210.

[8] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[9] Y. Bayar, Ö. Yorulmaz, O. Yelkesen, and V. Toader, “The interaction between ICT penetration and sustainable development: Empirical evidence from African countries,” Humanit. Soc. Sci. Commun., vol. 11, no. 1, 2024, doi: 10.1057/s41599-024-04174-z.

[10] E. T. Lwoga and R. Z. Sangeda, “ICTs and development in developing countries: A systematic review of reviews,” Inf. Syst. Develop., vol. 29, no. 2, pp. 1–20, 2019, doi: 10.1002/isd2.12060.

[11] UNESCO, Global Education Monitoring Report 2023. Paris, France: UNESCO Publishing, 2023.

[12] F. C. Aguboshim and C. C. Nwokedi, “Usability factors affecting the adoption of ICT-based innovations among female genders in Nigeria,” IOSR J. Mobile Comput. Appl., vol. 6, no. 4, pp. 1–6, 2019, doi: 10.9790/0050-06040106.

[13] O. O. David, “ICT diffusion and economic growth in Southern African Development Community (SADC) countries,” in New Perspectives and Paradigms in Applied Economics and Business. Cham, Switzerland: Springer, 2024, pp. 223–241, doi: 10.1007/978-3-031-49951-7_16.

[14] S. A. Asongu and P. N. Acha-Anyi, “Enhancing ICT for productivity in Sub-Saharan Africa: Thresholds for complementary policies,” Afr. J. Sci., Technol., Innov. Develop., vol. 12, no. 7, pp. 831–845, 2020, doi: 10.1080/20421338.2020.1732596.

[15] T. Coelli, “A multi-stage methodology for the solution of orientated DEA models,” Oper. Res. Lett., vol. 23, nos. 3–5, pp. 143–149, 1998, doi: 10.1016/S0167-6377(98)00036-4.

[16] W. D. Cook and L. M. Seiford, “Data envelopment analysis (DEA): Thirty years on,” Eur. J. Oper. Res., vol. 192, no. 1, pp. 1–17, 2009, doi: 10.1016/j.ejor.2008.01.032.

[17] R. Färe, S. Grosskopf, and C. A. K. Lovell, Production Frontiers. Cambridge, U.K.: Cambridge Univ. Press, 1994.

[18] P. Tyagi, S. P. Yadav, and S. P. Singh, “Relative performance of academic departments using DEA with sensitivity analysis,” Eval. Program Plann., vol. 32, no. 2, pp. 168–177, 2009, doi: 10.1016/j.evalprogplan.2008.10.002.

[19] G. Brown, “Ensemble learning,” in Encyclopedia of Machine Learning, C. Sammut and G. I. Webb, Eds. Boston, MA, USA: Springer, 2010, pp. 312–320.

[20] L. Breiman, Manual: Setting Up, Using, and Understanding Random Forests V4.0. Berkeley, CA, USA: Dept. Stat., Univ. California, Berkeley, 2003.

[21] I. H. Sarker, “Machine learning: Algorithms, real-world applications, and research directions,” SN Comput. Sci., vol. 2, no. 3, Art. no. 160, 2021, doi: 10.1007/s42979-021-00592-x.