go-v.orgdoi

SISTEM KLASIFIKASI KEBUTUHAN PERSEDIAAN SUKU CADANG KENDARAAN MENGGUNAKAN METODE K-NEAREST NEIGHBOR

Sry Yunarti, Saharuddin Saharuddin, Kurnia Yahya · Jurnal Informatika Progres · 2026

  • DOI 10.56708/progres.v18i2.494
  • Publisher OpenAlex
  • Type article
  • Issued 2026

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

Jurnal Informatika Progres · OpenAlex · article · 2026

Abstract

Inaccuracies in predicting vehicle spare part demands often result in overstocking or stockout issues, which adversely affect company operations. This study aims to classify the level of spare part requirements at PT Sinar Galesong Pratama Makassar into three categories (High, Medium, and Low) using the K-Nearest Neighbor (KNN) algorithm. The dataset comprises 42 sales transaction records subjected to a data preprocessing pipeline, including One-Hot Encoding for categorical variables, Sine-Cosine Transformation for monthly temporal features, and Z-Score Normalization for numerical attributes.

Model evaluation conducted using a Confusion Matrix on the testing data demonstrates that the KNN algorithm achieves a classification accuracy rate of 67%. This accuracy rate is influenced by the dynamic distance computation of KNN compared to the static threshold rules applied by the company. The practical implication of this research provides initial recommendations for management to optimize automated spare part procurement planning.

Open the resolved locator · 10.56708/progres.v18i2.494

Metadata licence: OpenAlex metadata (CC0)