Comparison of Random Forest and Gradient Boosting Methods for Multi-Product Demand Forecasting at CV Healfit Pangan Sehat (DietGo Kitchen) with Different Demand Characteristics

Article Sidebar

PDF
Published: Jun 30, 2026
DOI: https://doi.org/10.28932/jis.v9i1.15125
Keywords:
error, feature engineering, forecasting, Gradient Boosting, Random Forest

Main Article Content

Nisa Noviani Sudarman
Program Studi Teknik Industri, Fakultas Teknik, Universitas Ma’soem, Bandung, Indonesia
Gina Rahayu Wardiani
Program Studi Teknik Industri, Fakultas Teknik, Universitas Ma’soem, Bandung, Indonesia
Ladzwina Mahardini
Program Studi Rekayasa Logistik, Fakultas Sains dan Teknologi, Universitas Taruna Bakti, Bandung, Indonesia

Abstract

Accurate demand forecasting is a crucial factor in culinary industry supply chain management. This study compares the performance of two ensemble learning methods, namely Random Forest and Gradient Boosting, in predicting demand for six culinary products with different demand characteristics. The data used consists of monthly sales data at CV Healfit Pangan Sehat (DietGo Kitchen). Models were evaluated using Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results show that Random Forest delivered superior performance for 5 out of 6 products with an average MAPE of 31.61%, compared to Gradient Boosting with an average MAPE of 35.43%. Random Forest proved more robust in handling products with stable demand patterns (Sei Ayam: MAPE 19.76%, Sei Sapi: MAPE 21.38%) and intermittent demand (Sei Domba: MAPE 26.88%). Feature importance analysis revealed that lag-3, lag-6, and trend were the strongest predictors in both models. Gradient Boosting outperformed Random Forest on only one product (Sambal Bawang: MAPE 37.16%). High-volatility products such as Baked Grill Chicken yielded a MAPE of 32.98%. This study provides a practical contribution in the form of a forecasting method selection framework based on product demand characteristics, along with recommendations for implementation in the culinary industry.

Downloads

Download data is not yet available.

Article Details

How to Cite
Sudarman, N. N., Wardiani, G. R., & Mahardini, L. (2026). Comparison of Random Forest and Gradient Boosting Methods for Multi-Product Demand Forecasting at CV Healfit Pangan Sehat (DietGo Kitchen) with Different Demand Characteristics. Journal of Integrated System, 9(1), 72–88. https://doi.org/10.28932/jis.v9i1.15125
Issue
Vol. 9 No. 1 (2026): Journal of Integrated System Vol. 9 No. 1 (June 2026)
Section
Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

By submitting an article with the title above and acceptance publication of the article, I declare that:

  • Articles have never been previously published in scientific journals, proceedings or other electronic journals.
  • I agree that the article copyright is fully owned by the Journal of Integrated System, Universitas Kristen Maranatha. Declaration of copyright transfer from the author's to the journal is done by completing the following form (Copyright Transfer Agreement). 

Journal of Integrated System (JIS) uses a Copyright policy under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.

References

Amalia, R., Siregar, M.N. and Nasution, A.A. (2024) ‘Comparative forecasting of Indonesian stock prices using ARIMA and SVR: a statistical learning approach’, Millennial: Journal of Management, Economics, Entrepreneurship, and Policy (MMEP), 4(7), pp.1–12. Available at: https://doi.org/10.18280/mmep.120711.

Bappenas (2021) Study report: Food loss and waste in Indonesia. Supporting the implementation of circular economy and low carbon development. Available at: https://lcdi-indonesia.id/wp-content/uploads/2021/07/Report-Kajian-FLW-ENG.pdf (Accessed: 8 July 2010).

Breiman, L. (2001) ‘Random Forests’, Machine Learning, 45(1), pp.5–32.

Breiman, L. and Cutler, A. (2003) Manual on setting up, using, and understanding random forest V4.0. Available at: http://oz.berkeley.edu/users/breiman/Using_random_forests_v4.0.pdf (Accessed: 8 July 2010).

Creswell, J.W. and Creswell, J.D. (2018) Qualitative, quantitative, and mixed methods approaches. Los Angeles: Sage.

Dora, M., Biswas, S., Choudhary, S., Nayak, R. and Irani, Z. (2021) ‘A system-wide interdisciplinary conceptual framework for food loss and waste mitigation strategies in the supply chain’, Industrial Marketing Management, 93, pp.492–508. Available at: https://doi.org/10.1016/j.indmarman.2020.10.013.

FAO (2011) Global food losses and food waste: extent, causes and prevention. Rome: Food and Agriculture Organization of the United Nations.

Fernández-Delgado, M. et al. (2014) ‘Do we need hundreds of classifiers to solve real world classification problems?’, Journal of Machine Learning Research, 15(1), pp.3133–3181.

Friedman, J.H. (2001) ‘Greedy function approximation: a Gradient Boosting machine’, The Annals of Statistics, 29(5), pp.1189–1232.

Hermawan, A. and Kusuma, P.D. (2023) ‘Perbandingan Gradient Boosting dan Random Forest untuk demand forecasting retail’, Jurnal Teknik Industri Indonesia, 9(2), pp.145–156.

Hutasuhut, A.H., Anggraeni, W. and Tyasnurita, R. (2014) ‘Pembuatan aplikasi pendukung keputusan untuk peramalan persediaan bahan baku produksi plastik blowing dan inject menggunakan metode ARIMA (Autoregressive Integrated Moving Average) di CV Asia’, Jurnal Teknik ITS, 3(2), pp.A169–A174.

Kementerian Pariwisata dan Ekonomi Kreatif Republik Indonesia (2023) Statistik ekonomi kreatif Indonesia 2023. Jakarta: Kemenparekraf RI.

Kristanti, F.T., Febrianta, M.Y. and Salim, D.F. (2024) ‘Predicting financial distress in Indonesian companies using machine learning’, Engineering, Technology & Applied Science Research, 14(4), pp.15418–15423. Available at: https://doi.org/10.48084/etasr.8520.

Makridakis, S., Spiliotis, E. and Assimakopoulos, V. (2022) ‘M5 accuracy competition: results, findings, and conclusions’, International Journal of Forecasting. Available at: https://doi.org/10.1016/j.ijforecast.2021.11.013.

Maricar, M.A. (2019) ‘Analisa perbandingan nilai akurasi moving average dan exponential smoothing untuk sistem peramalan pendapatan pada perusahaan XYZ’, Jurnal Sistem dan Informatika (JSI), 13(2), pp.36–45.

Møller Christensen, F.M. et al. (2021) ‘Developing new forecasting accuracy measure considering Product’s shelf life: effect on availability and waste’, Journal of Cleaner Production, 288, p. 125594. Available at: https://doi.org/https://doi.org/10.1016/j.jclepro.2020.125594.

Poore, J. and Nemecek, T. (2018) ‘Reducing food’s environmental impacts through producers and consumers’, Science, 360(6392), pp.987–992.

Pradiptyo, D.R. et al. (2024) ‘Incorporating stock prices and social media sentiment for stock market prediction: a case of Indonesian banking company’, Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI), 13(1), pp.156–165. Available at: https://doi.org/10.23887/janapati.v13i1.74486.

Smyl, S. (2020) ‘A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting’, International Journal of Forecasting, 36(1), pp.75–85. Available at: https://doi.org/10.1016/j.ijforecast.2019.03.017.

Sudarman, Noviani and Nisa (2024) ‘Analisis perbandingan metode forecasting demand untuk optimasi persediaan bahan baku di DietGo Kitchen’, Jurnal Industrial Galuh, 7(2), pp.92–99.

Subagyo, P. (1986) Forecasting: Konsep dan aplikasi. Yogyakarta: BPPE UGM.

Syntetos, A.A. and Boylan, J.E. (2005) ‘The accuracy of intermittent demand estimates’, International Journal of Forecasting, 21(2), pp.303–314. Available at: https://doi.org/10.1016/j.ijforecast.2004.10.001.

Zulfia, A., Wibisono, M.A. and Setiawan, B. (2025) ‘AI decision support system for demand forecasting and retail stock management using Random Forest algorithm’, Brilliance: Research of Artificial Intelligence, 5(1), pp.45–58. Available at: https://doi.org/10.47709/brilliance.v5i1.3456.