Penerapan Data Mining dalam Menentukan Kategori Barang Rongsokan Berdasarkan Frekuensi Penjualan Menggunakan Algoritma Naive Bayes

This study is motivated by the manual transaction recording system at Lapak Pak Iyan, a micro, small, and medium enterprise (MSME) engaged in scrap goods collection in Rawalumbu, East Bekasi. This condition makes it difficult to identify frequently traded types of scrap goods, so purchasing decisions are not yet supported by structured data. This study aims to apply data mining using the Naive Bayes algorithm to classify scrap goods based on sales frequency into three categories: High-Selling, Moderate-Selling, and Low-Selling. The research methods include data collection, preprocessing, frequency calculation, category labeling, and classification using RapidMiner Studio. The data consist of 63 transaction records from January to June 2026 covering seven types of scrap goods. Model testing was conducted using Leave-One-Out Cross Validation (LOOCV) because of the small final dataset. The results show that Naive Bayes successfully classified the scrap goods into three categories with an accuracy of 100%. The classification results can be used as a reference for the owner of Lapak Pak Iyan in determining scrap goods purchasing priorities more efficiently.