The thesis focused on three forecasting techniques: moving average (MA), simple exponential smoothing (SES), and triple exponential smoothing (TES) with seasonality and trend. The research compared the performance of these methods by analyzing their statistical errors, specifically the Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The evaluation involved four different product categories: grocery store, meat products, raw materials, and beverages & wines. The objective was to determine the most suitable forecasting method for each category to approximate real demand values accurately. The findings revealed that the moving average method consistently exhibited the smallest statistical error in three out of four comparisons. It demonstrated superior performance in forecasting demand for a grocery store, meat products, and raw materials. The low MAD and MAPE values indicated that the moving average method provided accurate estimates that closely aligned with the actual demand curves in these categories. However, in the case of forecasting beverages and wines, the simple exponential smoothing method outperformed the other techniques. It yielded the lowest statistical error, suggesting its suitability for accurately predicting demand in this specific product category. The thesis highlighted the importance of selecting an appropriate forecasting method based on the characteristics of the data and the specific context. The results emphasized the effectiveness of predictive models in improving inventory management practices in the restaurant services industry. By employing these models, restaurant owners and managers can make informed decisions regarding inventory replenishment and minimize costs associated with overstocking or stockouts. This thesis contributes to the field of inventory management by providing insights into the application of predictive models in the specific context of restaurant services. The findings can guide practitioners in choosing the most suitable forecasting method for different product categories, ultimately leading to enhanced inventory control and optimized operations. Future research could focus on exploring additional forecasting techniques or incorporating other factors such as seasonality, promotions, and external factors like weather conditions to further improve the accuracy of demand forecasting in the restaurant services industry.