Application of Decision Tree Algorithm in Determining the Quality of Processed Coffee Based on Consumer Preferences at Beskabean Coffee

This research aims to apply the Decision Tree algorithm in determining the quality of processed Beskabean coffee based on consumer preferences. Beskabean coffee is one of the local coffee products that is unique in its flavor, processing method, and brewing variety. In the face of market competition and rising consumer expectations, a deep understanding of the factors that influence preferences is essential to support product innovation. Data collection was conducted through distributing questionnaires to consumers who have tasted various variants of Beskabean coffee. The variables analyzed included acidity, viscosity, aroma, aftertaste, and brewing methods such as V60, French press, and tubruk. All data collected was then analyzed using the Decision Tree algorithm with the Classification and Regression Tree (CART) approach. The results of the analysis show that aroma and aftertaste are the two most dominant factors influencing consumer preferences for Beskabean coffee. The Decision Tree model successfully categorizes coffee quality based on a combination of sensory attributes and consumer preferences with a fairly high level of accuracy. These findings provide valuable insights for coffee businesses, especially MSMEs, to develop products that are more in line with market desires. The application of the Decision Tree algorithm is proven to be effective in identifying consumer decision patterns and can be used as a decision-making system.