IT Job Market Forecasting in East Africa: An ML Approach
DOI:
https://doi.org/10.17072/1993-0550-2026-1-92-99Ключевые слова:
IT Industry, workforce strategy, job market analysis, technology demand forecasting, technological innovation demand forecasting, machine learning, Artificial Neural NetworkАннотация
This study focuses on forecasting the Information Technology (IT) job market in East Africa (specifically Kenya, Uganda, and Tanzania) using machine learning (ML) models. The research utilizes a dataset of 1,048,576 job postings collected from online platforms, including LinkedIn and Indeed. A comparative analysis of forecasting models Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Long Short-Term Memory (LSTM), and Holt's linear trend was conducted to predict employment trends, seasonality, and residual patterns. The models were evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The LSTM model demonstrated superior performance with an MAE of 2.75, MSE of 15.90, and RMSE of 3.99. The RMSE value of 3.99 indicates that the model's predictions are, on average, within approximately 4 job postings of the actual values. The findings confirm the applicability of ML models for reliable labor market forecasting in the region, providing valuable insights for stakeholders in education, policy, and industry to align strategies with market demands.Библиографические ссылки
Senthurvelautham, S. and Senanayake, N. (2023), "A Machine Learning-Based Job Forecasting And Trend Analysis System To Predict Future Job Markets Using Historical Data", IEEE 8th International Conference for Convergence in Technology (I2CT), Lonavla, India, pp. 1−7, doi: 10.1109/I2CT57861.2023.10126233.
Li, W. and Law, K. L. E., (2024), "Deep Learning Models for Time Series Forecasting: A Review", IEEE Access, vol. 12, pp. 92306–92327, doi: 10.1109/ACCESS.2024.3422528.
Ray, S., Lama, A., Mishra, P., Biswas, T., Sankar Das, S. and Gurung, B. (2023), "An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique", Appl Soft Comput, vol. 49, p. 110939, doi: 10.1016/J.ASOC.2023.110939.
"Introduction to ARIMA models", (2024), URL: https://people.duke.edu/~rnau/411arim.htm (accessed: 02.04.2025).
Alrweili, H., Probab, H. F.-J. S. A. and undefined (2024), "Forecasting crude oil prices using an ARIMA-ANN hybrid model", digitalcommons.aaru.edu.jo, URL: https://digitalcommons.aaru.edu.jo/cgi/viewcontent.cgi?article=1505&context=jsap (ac-cessed: 02.04.2025).
Sarker, I. H., (2021), "Machine Learning: Algorithms, Real-World Applications and Research Directions", SN Comput Sci, vol. 2, no 3, pp. 1−21, May 2021, doi: 10.1007/S42979-021-00592-X/FIGURES/11.
C. D.-I. J. of E. E. and Policy and undefined (2024), "The performance of hybrid ARIMA-GARCH modeling and forecasting oil price", zbw.eu, URL: https://www.zbw.eu/econis-archiv/bitstream/11159/2094/1/1028123450.pdf (accessed: 02.04.2025).
Lim, B. and Zohren, S. (2021), "Time-series forecasting with deep learning: A survey", Philosophical Transactions of the Royal Society A: Mathematical Physical and Engineer-ing Sciences, vol. 379, no 2194, doi: 10.1098/RSTA.2020.0209.
Hoong Lem, K. "The STL-ARIMA approach for seasonal time series forecast: a preliminary study", doi: 10.1051/itmconf/20246701008.
Tihi, N. and Popov, S. (2024), "The Higher Education Technical School of Professional Studies in Novi Sad, a comparison of Arima and random forest time series models for urban drought prediction", Computer Science, and Data Science, doi: 10.15308/Sinteza-2024-51-56.
Casolaro, A., Capone, V., Iannuzzo, G. and Camastra, F. (2023), "Deep Learning for Time Series Forecasting: Advances and Open Problems", Information 2023, Vol. 14, Page 598, vol. 14, no 11, p. 598, doi: 10.3390/INFO14110598.
Nazir, A. et al., (2024), "A deep learning-based novel hybrid CNN-LSTM architecture for efficient detection of threats in the IoT ecosystem", Ain Shams Engineering Journal, vol. 15, no 7, p. 102777, doi: 10.1016/J.ASEJ.2024.102777.
Zhu, W. et al., (2023), "An optimized long short-term memory (LSTM)-based approach applied to early warning and forecasting of ponding in the urban drainage system", Hydrol Earth Syst Sci, vol. 27, no 10, pp. 2035–2050, May 2023, doi: 10.5194/HESS-27-2035-2023.
Загрузки
Опубликован
Как цитировать
Выпуск
Раздел
Лицензия
Copyright (c) 2026 Ребекка Ндунги , Иван Станиславович Блеканов
Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.
Публикация статьи в журнале осуществляется на условиях лицензии Creative Commons Attribution 4.0 International (CC BY 4.0).
