PENERAPAN ALGORITMA K-NEAREST NEIGHBOR DALAM ANALISIS PEMINJAMAN BARANG PADA DIVISI INVENTARIS TVRI MAKASSAR
Risal, Chyquitha Danuputri, Darniati, Muhyiddin AM Hayat · Jurnal Informatika Progres · 2025
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 · 2025
Abstract
Inventory management in the TVRI Makassar Inventory Division is inefficient due to the lack of a predictive system, hampering proactive asset requirement planning. This study aims to apply the K-Nearest Neighbor (KNN) algorithm to analyze historical borrowing patterns, predict demand for goods three months in advance, and evaluate model accuracy. Using a quantitative approach, this study implements a systematic machine learning workflow, including data preprocessing, temporal feature engineering, class imbalance handling using the Synthetic Minority Over-sampling Technique (SMOTE), and hyperparameter optimization using GridSearchCV.
The results show that the optimized KNN model achieved an overall accuracy of 80.18%, significantly outperforming the baseline model. Key findings revealed that the model's performance is contextual, with very high reliability (F1-Score > 0.95) on frequently borrowed assets, and is able to identify strong temporal demand patterns. It is concluded that KNN is effective for segmented inventory demand prediction and has the potential to serve as a basis for TVRI Makassar to adopt a proactive, data-driven inventory management strategy, enabling more efficient resource allocation.
Open the resolved locator · 10.56708/progres.v17i2.474
Metadata licence: OpenAlex metadata (CC0)