An innovative web application for forecasting Malaysia’s unemployment rate using ARIMA and exponential smoothing techniques

Unemployment is one of the most significant socio-economic issues faced by many countries, as it reflects both economic stability and social well-being. Accurate forecasting of unemployment trends can help policymakers and stakeholders in making informed decisions to improve labour market conditions. This study aims to develop a forecasting model for unemployment rates using time series approaches and deploy it into an interactive Shiny web application. Data were obtained from publicly available unemployment statistics and analysed using ARIMA and ETS models. The forecasting results demonstrated that both models provide reliable projections, with ARIMA showing slightly higher accuracy based on error metrics such as RMSE and MAPE. The Shiny application enables users to visualise historical unemployment data, compare model performance, and generate forecasts interactively. The findings highlight the importance of integrating statistical forecasting with user-friendly technology platforms, providing accessible decision-making tools for researchers, policymakers, and the public.