Dynamic Pricing Optimization for Coffee Shops Using a Machine Learning Approach with Random Forest Models

This study looks at how dynamic pricing can help coffee shops make more revenue using machine learning. It uses three months of sales data to find patterns and predict the effects of price changes. Simulations show that raising prices by 10% during afternoon peak hours brings the most revenue, while discounts and other adjustments also boost profits. A Random Forest model, with a strong predictive score (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.984), captures the trends effectively. The results highlight how machine learning combined with point-of-sale systems can create smarter pricing strategies that match customer habits, driving both profits and satisfaction.