Prediksi Permintaan Resistor Menggunakan Implementasi Manual Gradient Boost Untuk Optimasi Inventaris
Keywords:
Gradient Boosting manual, machine learning, optimasi inventaris, prediksi permintaan, resistor, time series forecastingAbstract
Penelitian ini bertujuan mengoptimalkan inventaris resistor bulanan di toko komponen elektronik melalui prediksi permintaan yang akurat. Mengatasi tantangan overstock dan understock yang memicu kerugian investasi, model Gradient Boosting diimplementasikan secara manual. Model ini, yang dibangun berdasarkan prinsip dasar Extreme Gradient Boosting (XGBoost), dilatih menggunakan data historis permintaan resistor dari tiga bulan sebelumnya. Evaluasi kinerja model selama 20 iterasi pelatihan menunjukkan penurunan konsisten pada metrik Mean Absolute Error (MAE) dan Root Mean Squared Error (RMSE), mengindikasikan pembelajaran yang efektif. Model berhasil memprediksi permintaan Bulan-4 dan Bulan-5 menggunakan pendekatan "geser waktu". Meskipun sudah menunjukkan kemampuannya dalam memprediksi, penelitian ini dibatasi oleh penggunaan dataset simulasi yang sangat kecil (5 baris), dapat menyebabkan overfitting dan membatasi generalisasi. Hasil ini berfungsi sebagai ilustrasi metodologi dan validasi konsep dasar Gradient Boosting dalam mendukung keputusan inventaris. Untuk aplikasi nyata, diperlukan dataset lebih besar dan implementasi teroptimasi (misalnya, dengan library XGBoost) di masa mendatang
References
Vaka, D. K., “Integrating Inventory Management and Distribution: a Holistic Supply Chain Strategy,” International Journal of Managing Value and Supply Chains (IJMVSC), vol. 15, no. 2, pp. 13, Jun. 2024.
V. Pasupuleti, B. Thuraka, C. S. Kodete, and S. Malisetty, “Enhancing Supply Chain Agility and Sustainability through Machine Learning: Optimization Techniques for Logistics and Inventory Management,” Logistics, vol. 8, no. 3, p. 73, 2024, doi: 10.3390/logistics8030073
Mweshi, G. K., “Effects of Overstocking and Stockouts on the Manufacturing Sector,” International Journal of Advances in Engineering and Management (IJAEM), vol. 4, no. 9, pp. 1054–1064, Sep. 2022. DOI: 10.35629/5252-040910541064
R. Winurputra dan D. E. Ratnawati, “Peramalan Penjualan Produk Menggunakan Extreme Gradient Boosting (XGBOOST) Dan Kerangka Kerja Crisp-Dm untuk Pengoptimalan Manajemen Persediaan (Studi Kasus: Ub Mart)”, JTIIK, vol. 12, no. 2, pp. 417–428, Apr. 2025, doi: 10.25126/jtiik.2025129451.
S. B. Dalimunthe, R. . Ginting, and S. Sinulingga, “The Implementation Of Machine Learning In Demand Forecasting : A Review Of Method Used In Demand Forecasting With Machine Learning”, j.sist.teknik.industri., vol. 25, no. 1, pp. 41–49, Jan. 2023. DOI: https://doi.org/10.32734/jsti.v25i1.9290
P. Dankorpho, “Sales Forecasting for Retail Business Using XGBoost Algorithm,” Journal of Computer Science and Technology Studies, vol. 6, no. 2, pp. 136–141, Jun. 2024, DOI: https://doi.org/10.32996/jcsts.2024.6.2.15
B. Auffarth, *Machine Learning for Time-Series with Python: Forecast, predict, and detect anomalies with state-of-the-art machine learning methods*. Packt Publishing Ltd, 2021.
Y. Tadayonrad and A. B. Ndiaye, “A new key performance indicator model for demand forecasting in inventory management considering supply chain reliability and seasonality,” Supply Chain Analytics, vol. 3, p. 100026, 2023. https://doi.org/10.1016/j.sca.2023.100026
K. Kanike, “Factors disrupting supply chain management in manufacturing industries,” Journal of Supply Chain Management Science, vol. 4, no. 1-2, pp. 1–24, 2023. https://doi.org/10.18757/jscms.2023.6986
T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proc. ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
J. H. Friedman, “Greedy function approximation: a gradient boosting machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001.
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009.
