IT Job Market Forecasting in East Africa: An ML Approach

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.