This study explores the use of machine learning algorithms to forecast daily sales for BNK Cafe, leveraging two years of historical sales data. The research evaluates the performance of four machine learning models—Support Vector Machine (SVM), Linear Regression, Random Forest, and XGBoost—on weekly and monthly resampled datasets. Feature engineering techniques were applied to extract temporal patterns, while model performance was assessed using RMSE, MAPE, and R² metrics. XGBoost emerged as the most accurate model, excelling in capturing complex trends and seasonal variations, followed by Random Forest. Linear Regression served as a baseline, while SVM showed moderate success. Findings highlight the potential of advanced machine learning methods in improving inventory management, waste reduction, and operational efficiency in the food and beverage industry. Future work suggests incorporating contextual data and extending the analysis to multi-year trends for enhanced predictive accuracy.