Product Stock Supply Analysis System with FP Growth Algorithm

Abstract

This study explores the application of Data Mining in deciphering consumer purchasing patterns at Tani Heritage Shop, a retailer specializing in agricultural products. Facing the challenge of managing a high volume of daily sales transactions, the shop often encounters difficulties in tracking which products are frequently purchased together. This lack of insight leads to a critical issue: popular products running out of stock unexpectedly. To address this, the research focuses on developing a product stock supply analysis system, utilizing the FP Growth Algorithm. The FP Growth Algorithm, a powerful tool in Data Mining, is employed to analyze sales transaction data and identify consumer purchasing trends, particularly products bought simultaneously. This approach is designed to provide insights into optimal stocking strategies, ensuring the availability of in-demand products. The research methodology involves applying the FP Growth Algorithm to model the product stock supply system, using specific sales data attributes. The results of this study are significant. By setting parameters such as a minimum support value of 30%, a confidence value of 70%, and targeting the highest lift ratio value of 3.67, the research successfully derives several key association rules from the FP Growth algorithm. These rules are instrumental in optimizing the product stock supply analysis system.

Keywords

• association rule, extreme programming, fp-growth, supply analysis