Sales Information System Using FP-Growth Algorithm Based on Consumer Purchasing Patterns

The advancement of technology has driven businesses to innovate digitally to improve operational efficiency and effectiveness, including in the food and beverage industry. Two Much Coffee & Roastery is one of the cafes that still operates in a semi-digital manner, recording transactions manually using Microsoft Excel. The cafe faces challenges in optimizing sales strategies, particularly in implementing cross-selling strategies, as there is no system that provides automatic product recommendations. This study aims to implement data mining techniques using the FP-Growth algorithm to identify consumer purchasing patterns from historical transaction data. The algorithm was applied with a minimum support of 0.01 and a lift of 1.0, resulting in 30 association rules. These rules were integrated into a web-based system used by the cashier to support cross-selling strategies. The system not only records transactions but also provides product recommendations based on previous purchasing patterns, which is expected to effectively and efficiently increase the cafe’s sales.