Penerapan Data Mining dalam Pengendalian Persediaan Produk Furniture pada PT Starindo Prima

Abstract

The advancement of technology has led to the onset of the Fourth Industrial Revolution, where the physical, digital, and biological worlds are integrated. Trends such as automation, the Internet of Things (IoT), big data, and cloud computing technologies dominate this era. Data science, in particular, has become crucial, helping to transform data into meaningful information. Data mining has also rapidly developed, driven by advancements in information technology and the internet. Currently, the furniture industry is one of the sectors influencing Indonesia's economy. The demand for furniture continues to increase over time due to various innovations in the furniture being produced. Therefore, PT Starindo Prima, one of the industries in the furniture sector, must always provide its products to meet customer demands. However, in 2023, PT Starindo Prima faced several challenges, such as the unavailability or shortage of stock when customer demand occurred. This issue necessitated PT Starindo Prima to produce the products first, resulting in delivery times of 1-2 months. The improper stock provision has been a major issue causing these problems. Data mining processes on transaction data become a solution to identify customer purchase patterns to determine products for which safety stock and reorder points will be calculated, ensuring product stock is always maintained. This study uses one of the data mining techniques, namely association techniques, to analyze customer purchase patterns. By using the FPGrowth algorithm, customer purchase patterns will be generated and analyzed to obtain product recommendations for production. The results include 11 association rules formed with a minimum support of 0.03 or 3% and a minimum confidence of 0.5 or 50%. The products generated based on the association rules amount to 12 products with an estimated safety stock ranging from 33 to 66 units and reorder points ranging from 53 to 106 units