This paper presents a robust and new state-space framework for the formulation of the state-space ARIMA (SSARIMA) model. The SSARIMA model enhances the standard ARIMA model by utilizing the versatility and complexity of a state-space framework. We utilized state and observation equations to develop the SSARIMA model, facilitating a more refined representation of the time series dynamics. This framework offers an alternative, perhaps more precise method for time series forecasting by modeling the data creation process to incorporate both observed and latent factors affecting the series. We tested our new SSARIMA formulation with monthly data on Hungarian energy usage to see how it stacked up against the tried-and-true ARIMA model for making predictions. According to our results, the SSARIMA model showed better predicting accuracy than ARIMA, which was already performing at a high level. The study’s findings suggest that the SSARIMA model could be a powerful tool for time series analysis, especially in fields where understanding the deeper structural and state-driven aspects of the data is crucial. The enhanced accuracy achieved by SSARIMA highlights its promise as a method that could bridge the gap between classical time series modeling and more complex, data-driven approaches, offering both predictive accuracy and interpretability. This framework provides a new avenue for researchers and practitioners aiming to enhance forecasting performance in time series analysis.