Abstract
The high unemployment rate, especially among the youth in South Africa, necessitates addressing the skills requirements to meet the labour market demands. In South Africa, the Sector Education and Training Authorities are mandated to identify and provide the skills demanded. A quantitative approach of big data analytics is proposed for predicting the future skills of the South African food and beverages manufacturing sector. The source of big data is skills-related publications from the Elsevier Scopus database, for the period 1999 to 2020. Natural language processing, and word representation technique was applied to quantify and analyse year-on-year change of author and index keywords, subject areas and number of publications towards the determination of the future skills requirement. The analysis identified four vital skills: (1) entrepreneurship inclusive of digital skills; (2) data analytics inclusive of AI, simulation, and modelling; (3) digital tools and technologies implementation, and operation; and (4) sustainable operations skills of advanced process control, and energy, water, and resource optimisation. The identified skills were comparatively analysed with the World Economic Forum predictions for skills requirements for 2025, with the results aligning to the findings and validating the approach. The approach is applicable to any Sector Education Training Authority in South Africa. This enables enhanced skills planning to better prepare the South African workforce, especially youth, given the persistent challenges to completion of Grade 12 leading to access to higher education. It is acknowledged that youth with tertiary qualifications have a better chance of employment than those without, thus skills planning initiatives is essential. The skills gap cannot be instantaneously addressed but requires a long-term strategic effort from all stakeholders in the skills ecosystem. As a starting point in youth skills development, short courses to workshops to workplace training is a feasible option.
References
British Council. (2018). Futureskills in India foundation. British Council.
CEDEFOP. (2019). The online job vacancy market in the EU. CEDEFOP.
CoPs. (2022). The Monash model. University of Melbourne. https://www.copsmodels.com/monmod.htm
DHET. (2019). Skills, supply and demand in South Africa. DHET.
Elgendy, N., Elragal, A., & Päivärinta, T. (2022). DECAS: a modern data-driven decision theory for big data and analytics. Journal of Decision Systems, 31(4), 337–373. https://doi.org/10.1080/12460125.2021.1894674
Elgral, A., & Klischewski, R. (2017). Theory-driven or priocess-driven prediction? Epistemological challenges of big data analytics. Journal of Big Data, 1–20.
Elsevier Scopus. (2025, February). Scopus content. Retrieved from Elsevier: https://www.elsevier.com/products/scopus/content#0-content-coverage
Employment and Social Development Canada. (2022). Canadian Occupational Projection System(COPs).
ETF. (2016). Developing skills foresights, scenarios and forecasts. Guide to anticipating and matching skills and jobs (Vol 2). ETF.
Gandomi, A., & Haider, M. (2015). Beyond the hype: Big data concepts, methods and analytics. International journal of infromation management, 35(2), 137–144. https://doi.org/10.1016/j.ijinfomgt.2014.10.007
Governmemnt of Canada. (2023). Canadian Occupational Projection Systems (COPs). Retrieved from https://occupations.esdc.gc.ca/sppc-cops/l.3bd.2t.1ils@-eng.jsp
ILO. (2020). The feasibility of using big data in anticipating and matching skills needs. ILO.
ILO-OECD. (2018). Approaches to anticipating skills for the future of work. ILO-OCED.
LinkedIn. (2021). Future of skills. Retrieved from LinkedIn: https://linkedin.github.io/future-of-skills/
LinkedIn. (2022). Global green skills report. LinkedIn.
Maier, T. (2017). The BIBB-IAB Qualification and Occupational Field Projections (QuBe-Projekt.de).
Mezzanzanica, M., & Mercorio, F. (2019). Big data for labour market intelligence. ETF.
National Skills Commission. (2022). Employment outlook: Industry and occupation trends over the five years to November 2026. Government of Australia. https://doi.org/10.1021/cen-v028n030.p2503
OECD. (2016). Getting skills right: Assessing and anticipating changing skills need. OECD.
Sabharwal, R., & Miah, S. (2021). A new theoretical understanding of big datra analytics capabilities in organizations: a thermatic analysis. Journal of Big Data, 8(1), 1–23. https://doi.org/10.1186/s40537-021-00543-6
Statistics South Africa (a). (2022). Quarterly labour force survey. Statistics South Africa.
Statistics South Africa (b). (2024). Labour market dynamics in South Africa 2023. Statistics South Africa.
Statistics South Africa (c). (2024). Quarterly Labour Force Survey Quarter 3–2024. Statistics South Africa.
U.S. Bureau of Labor Statistics. (2021). Employment projections - 2012–2022.
Wilson, R., Barnes, S.-A., May-Gillings, M., Patel, S., & Bui, H. (2020). Working Futures 2017–2027: Long-run labour market and skills projections for the UK. Department of Education.
World Economic Forum. (2020). The Future of Jobs Report 2020. http://www3.weforum.org/docs/WEF_Future_of_Jobs_2020.pdf

This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2025 Megashnee Munsamy, Arnesh Telukdarie