Implementation of Apriori Algorithm for Determining Spare Parts Product Recommendation Packages

Abstract

The aim of this research is to determine recommended product packages for spare parts from an automotive parts supplier. Shop owners have faced challenges in meeting customer demands over the past few months, experiencing frequent stockouts of spare parts due to a manual transaction recording system and a manual checking system for spare parts storage. This inefficiency and lack of accuracy in managing in-demand spare parts prompted the application of the apriori algorithm, a data mining method. Data was collected from the total sales over the past three months, subsequently cleaned and transformed for manual and Python-based apriori calculations. The results, obtained through both manual and Python implementations of apriori, indicate that the two frequently occurring item sets are oil filters with a confidence value of 68% and air filters with a confidence value of 63%. Based on these findings, the study recommends spare parts stores to maintain higher stock levels of oil filters and air filters compared to other spare parts.

Pola Pembelian Konsumen Dengan Metode Market Basket Analysis pada Perishable Product di Toko Roti Ikobana Bakery

“…Selanjutnya dilakukan analisa ketersediaan stok pada dua produk tersebut pada bulan berikutnya dengan Economic Order Quantity (EOQ). [19] meneliti tentang suku cadang kendaraan bermotor yang sering dibeli konsumen dengan algoritma apriori dengan dataset sejumlah 1220 transaksi penjualan dan ditemukan dua item set yang sering muncul yaitu filter oli dengan nilai kepercayaan (confidence) 68% dan filter udara dengan nilai kepercayaan 63%. Penelitian [20] di Toko Sayur Keluarga (TOSAGA) dengan total transaksi 33.462 dan 365 item barang dengan algoritma apriori digunakan untuk melihat pola perilaku konsumen.…”