Peramalan Tren Penjualan pada Sistem Informasi Inventory Barang Diecast Menggunakan Support Vector Regression

  • Imanuel Saragih Universitas 17 Agustus 1945 Surabaya
  • Ardy Januantoro Universitas 17 Agustus 1945 Surabaya
  • Bagus Hardiansyah Universitas 17 Agustus 1945 Surabaya
Keywords: inventory, prediction, forecasting, stock, supply, Support Vector Regression, SVR


Inventory management of diecast products is crucial for Sada Hobby store. The challenge in managing inventory lies in the importation of goods from overseas, which often lacks a definite delivery time, resulting in stock delays. An effective forecasting model is needed to address this challenge, such as Support Vector Regression (SVR), which can handle non-linear data using ε-sensitive approach. The SVR model predicts sales for each month in the next year, with accuracy measured using Mean Squared Error (MSE). The research results show that the SVR model estimates sales to be 8,423 units with an MSE accuracy of 0.0018. Sales predictions are also made for the Tomica brand (2,423 units, MSE 0.0019), Hotwheels brand (1,299 units, MSE 0.091), and Majorette brand (360 units, MSE 1.244). Although the MSE for these brands is higher than the overall sales prediction, the results are still good. The brand-based prediction process requires comparisons with all other brands, while the overall sales prediction sums up the sales results from all brands.


Download data is not yet available.

Author Biographies

Imanuel Saragih, Universitas 17 Agustus 1945 Surabaya

Teknik Informatika

Ardy Januantoro, Universitas 17 Agustus 1945 Surabaya

Sistem dan Teknologi Informasi

Bagus Hardiansyah, Universitas 17 Agustus 1945 Surabaya

Teknik Informatika


D. I. Purnama and S. Setianingsih, “Support Vector Regression (SVR) Model for Forecasting Number of Passengers on Domestic Flights at Sultan Hasanudin Airport Makassar,” J. Mat. Stat. dan Komputasi, vol. 16, no. 3, pp. 391–403, 2020.

D. Suprayogi and H. F. Pardede, “Support Vector Regression Dalam Prediksi Penurunan Jumlah Kasus Penderita COVID-19,” JOINTECS (Journal Inf. Technol. Comput. Sci., vol. 7, no. 2, pp. 63–70, 2022, doi:

R. S. Laminullah, H. Annur, and I. S. K. Idris, “Prediksi Penjualan Pertalite Menggunakan Metode Support Vector Regression,” J. Tek. Elektro CosPhi, vol. 4, no. 1, pp. 12–14, 2020.

X. Yu, Z. Qi, and Y. Zhao, “Support Vector Regression for Newspaper/Magazine Sales Forecasting,” Procedia Comput. Sci., vol. 17, pp. 1055–1062, 2013, doi:

G. H. Saputra, A. H. Wigena, and B. Sartono, “Penggunaan Support Vector Regression dalam Pemodelan Indeks Saham Syariah Indonesia dengan Algoritme Grid Search,” Indones. J. Stat. Its Appl., vol. 3, no. 2, pp. 148–160, 2019.

I. Permana and F. N. Salisah, “The Effect of Data Normalization on the Performance of the Classification Results of the Backpropagation Algorithm,” Indones. J. Inform. Res. Softw. Eng., vol. 2, no. 1, pp. 67–72, 2022, doi:

R. G. Whendasmoro and J. Joseph, “Analisis Penerapan Normalisasi Data dengan Menggunakan Z-Score pada Kinerja Algoritma K-NN,” JURIKOM (Jurnal Ris. Komputer), vol. 9, no. 4, pp. 872–876, 2022, doi:

R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice. Australia: OTexts: Melbourne, 2018.

N. T. Thomopoulos, Demand Forecasting for Inventory Control. Springer, Cham, 2014. doi:

R. P. Furi, J. Jondri, and D. Saepudin, “Prediksi Financial Time Series Menggunakan Independent Component Analysis dan Support Vector Regression Studi Kasus: IHSG dan JII,” in Proceedings of Engineering, 2015, vol. 2, no. 2, pp. 3608–3618. [Online]. Available:

M. Y. Darsyah, “Klasifikasi Tuberkulosis dengan Pendekatan Metode Supports Vector Machine (SVM),” J. Stat. Univ. Muhammadiyah Semarang, vol. 2, no. 2, pp. 37–41, 2014.

R. A. Putri, W. S. Winahju, and M. Mashuri, “Penerapan Metode Ridge Regression dan Support Vector Regression (SVR) untuk Prediksi Indeks Batubara di PT. XYZ,” J. Sains dan Seni ITS, vol. 9, no. 1, pp. D64–D71, 2020, doi: