IMPLEMENTATION OF DATA MINING ON MUSLIM WOMEN'S CLOTHING SALES USING THE FP-GROWTH METHOD

The Muslim women's fashion industry in Indonesia is growing rapidly, leading to intense competition and requiring business owners to optimize their sales strategies and inventory management. This study aims to identify consumer purchasing patterns at TM Collection Store by applying the FP-Growth data mining method. The data used consists of 1,000 sales transactions from January to April 2024. Data collection was conducted through historical data observation, interviews, and literature review, followed by processing using the FP-Growth algorithm in Google Colab. The analysis results reveal strong associations between products, such as the combination of Paris Premium, shirt cuffs XL, and shirt cuffs L, which show high confidence values and significant lift. These patterns provide valuable insights for decision-making related to restocking and promotional strategies. The findings also help improve operational efficiency by more accurately predicting customer demand. Therefore, the implementation of the FP-Growth algorithm proves effective in processing transaction data to generate relevant information and support more targeted business decisions. This data-driven strategy offers an innovative solution to enhance competitiveness in the continuously growing Muslim women's fashion industry.