This study focuses on forecasting the demand for components used in repair services within supply chain management. Accurate demand forecasting is crucial for avoiding stockouts and excessive inventory costs. One of the main challenges of this study is the scarcity of available data for many components, which made it difficult to build and evaluate effective predictive models. To overcome this limitation, the strategy of grouping interchangeable components was adopted, allowing the analysis of aggregated data for items used interchangeably in repair services. This study used historical data on warranty stock, placements, and the Consumption Index (IDC) for approximately 3,000 subgroups of electronic components. Classical time series techniques, including the Simple Moving Average (SMA) and Exponential Moving Average (EMA), are utilized alongside more advanced models, which encompass various implementation packages for SARIMAX models. Performance analysis was conducted using the Root Mean Square Error (RMSE) and Sufficiency metrics.