Model Prediksi Permintaan Produk Berbasis Big Data Analytics untuk Pengendalian Persediaan Multi-Produk

Authors

  • Almayandi Program Studi Teknik Industri, Universitas Jenderal Achmad Yani, Cimahi, Indonesia
  • Hanapi Program Studi Teknik Industri, Universitas Jenderal Achmad Yani, Cimahi, Indonesia
  • Haerul Azmi Program Studi Teknik Industri, Universitas Jenderal Achmad Yani, Cimahi, Indonesia

DOI:

https://doi.org/10.69503/ije.v5i2.1624

Keywords:

Big Data Analytics, Prediksi Permintaan, Machine Learning, Pengendalian Persediaan, Multi-Produk

Abstract

Abstrak: Penelitian ini bertujuan mengembangkan model prediksi permintaan produk berbasis Big Data Analytics untuk meningkatkan efektivitas pengendalian persediaan multi-produk. Permasalahan utama terletak pada rendahnya akurasi metode prediksi tradisional dalam menangani data kompleks dan dinamika permintaan yang tinggi. Penelitian ini menggunakan pendekatan kuantitatif berbasis data-driven dengan memanfaatkan data historis penjualan, perilaku konsumen, serta faktor eksternal seperti musim dan promosi. Model yang dikembangkan mengintegrasikan metode statistik, machine learning, dan deep learning dalam kerangka hybrid untuk menangkap pola linear dan non-linear secara simultan. Tahapan penelitian meliputi pengumpulan data, preprocessing, feature engineering, pelatihan model, serta evaluasi menggunakan metrik Mean Absolute Error (MAE) dan Root Mean Square Error (RMSE). Selain itu, teknik ensemble learning dan clustering diterapkan untuk meningkatkan akurasi dan stabilitas model. Hasil penelitian menunjukkan bahwa model hybrid berbasis Big Data Analytics mampu menghasilkan prediksi dengan tingkat akurasi lebih tinggi dibandingkan model tunggal. Model ini juga mampu menangkap interdependensi antar produk dalam sistem multi-produk secara lebih efektif. Integrasi hasil prediksi dengan kebijakan pengendalian persediaan seperti safety stock dan reorder point menunjukkan peningkatan efisiensi operasional melalui penurunan risiko overstock dan stockout. Selain itu, sistem yang dikembangkan mampu merespons perubahan permintaan secara lebih cepat dan adaptif. Penelitian ini memberikan kontribusi dalam pengembangan model prediksi yang tidak hanya akurat, tetapi juga aplikatif dalam mendukung pengambilan keputusan inventory di era digital.

Abstract: This study aims to develop a product demand forecasting model based on Big Data Analytics to improve the effectiveness of multi-product inventory control. The main problem lies in the low accuracy of traditional forecasting methods in handling complex data and high demand variability. This study employs a quantitative, data-driven approach by utilizing historical sales data, consumer behavior, and external factors such as seasonality and promotions. The proposed model integrates statistical methods, machine learning, and deep learning within a hybrid framework to simultaneously capture linear and non-linear patterns. The research stages include data collection, preprocessing, feature engineering, model training, and evaluation using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). In addition, ensemble learning and clustering techniques are applied to enhance model accuracy and stability. The results indicate that the hybrid model based on Big Data Analytics produces higher prediction accuracy compared to single models. The model effectively captures interdependencies among products within a multi-product system. The integration of forecasting results with inventory control policies, such as safety stock and reorder point, improves operational efficiency by reducing the risks of overstock and stockouts. Furthermore, the developed system responds more quickly and adaptively to demand fluctuations. This study contributes to the development of forecasting models that are not only accurate but also practical in supporting inventory decision-making in the digital era.

References

Abualuroug, S., Alzubi, A., & Iyiola, K. (2024). Inventory prediction using a modified multi-dimensional collaborative wrapped bi-directional long short-term memory model. Applied Sciences, 14(13), 5817. https://doi.org/10.3390/app14135817

Achakzai, M. K., Rehman, A., Ahmed, A., & Haider, S. O. (2025). The Role of Artificial Intelligence in Transforming Supply Chain Management: A Focus on Demand Forecasting and Inventory Optimization. The Critical Review of Social Sciences Studies, 3(2), 622-637. https://doi.org/10.59075/vs86kw78

Agarwal, R. (2025). Optimizing Inventory Forecasting with Big Data and Machine Learning Approaches. Journal of Quantum Science and Technology, 2(4), 55–66. https://doi.org/10.63345/jqst.v2i4.356

Ai, Z., Zhao, F., Hu, C., et al. (2024). Research on e-commerce product demand forecasting method based on ARIMA-SVR-PSO. IEEE Conference Proceedings, 778-783. https://doi.org/10.1109/icirdc65564.2024.00145

Ankam, S. (2025). AI-driven demand forecasting in enterprise retail systems: Leveraging predictive analytics for enhanced supply chain. IJSAT-International Journal on Science and Technology, 16(1). https://doi.org/10.71097/ijsat.v16.i1.2644

Baykal-G, M., & Erkip, N. (2011). Forecasting for inventory planning under correlated demand. In Wiley Encyclopedia of Operations Research and Management Science. https://doi.org/10.1002/9780470400531.eorms0330

Chen, J. (2024). Advanced analytics for retail inventory and demand forecasting. Transactions on Economics, Business and Management Research, 10, 113-119.

Duvaasi, V. (2025). How will strategic use of big data analytics transform retail supply chain management. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5005736

Elorza, M., Castellano, E., & Segura, S. (2025). Prediction of customer demand for perishable products in retail inventory management, using the hybrid prophet-XGBoost model during the post-COVID-19 period. Applied Economics Letters, 32(17), 2453-2459. https://doi.org/10.1080/13504851.2024.2333995

Hu, L., & Han, W. (2024). Research on supply chain demand forecasting and dynamic adjustment model based on big data and artificial intelligence. IEEE Conference Proceedings, 153-159. https://doi.org/10.1109/iist62526.2024.00100

Kalisetty, S. (2023). Harnessing Big Data and Deep Learning for Real-Time Demand Forecasting in Retail: A Scalable AI-Driven Approach. American Online Journal of Science and Engineering, 1(1). https://doi.org/10.5281/zenodo.16418819

Li, X., Zheng, Y., Zhou, Z., & Zheng, Z. (2019). Demand prediction, predictive shipping, and product allocation for large-scale e-commerce. Predictive Shipping, and Product Allocation for Large-Scale E-Commerce.

Luan, Y. (2024). Construction and Application Research of Beer Category Sales Forecasting Model Based on Big Data Analysis for Supermarket X. International Journal of Emerging Technologies and Advanced Applications, 1(10), 1-9. https://doi.org/10.62677/ijetaa.2410128

Mohan, V., & Kurian, S. (2023). Product Demand Prediction. Proceedings of the National Conference on Emerging Computer Applications (NCECA), 370–373. https://doi.org/10.5281/zenodo.7956736

Murni, C. K., Choiri, A. F., & Rahmawati, F. D. (2025). Product Demand Forecasting in E-Commerce with Big Data Analytics: Personalization, Decision Making and Optimization. Journal of Informatics Development, 3(2), 1-6. https://doi.org/10.30741/jid.v3i2.1548

Nagarajan, D., Bhuvaneswari, T., & Suppiah, Y. (2025). Intelligent inventory prediction using random forest. Edelweiss Applied Science and Technology, 9(4). https://doi.org/10.55214/25768484.v9i4.6383

Olatunji, A. O. (2025). Leveraging Data Science for Demand Forecasting and Inventory Management: A Comprehensive Review. J. Basic Appl. Res. Int, 31, 29-38.

Schmidt, F. G., & Pibernik, R. (2025). Data-driven inventory control for large product portfolios: A practical application of prescriptive analytics. European Journal of Operational Research, 322(1), 254-269. https://doi.org/10.1016/j.ejor.2024.10.012

Sekhar, C. (2022). Optimizing Retail Inventory Management with AI: A Predictive Approach to Demand Forecasting, Stock Optimization, and Automated Reordering. European Journal of Advances in Engineering and Technology, 9(11), 89–94. https://doi.org/10.5281/zenodo.13325333

Seyedan, M., Mafakheri, F., & Wang, C. (2023). Order-up-to-level inventory optimization model using time-series demand forecasting with ensemble deep learning. Supply Chain Analytics, 3, 100024. https://doi.org/10.1016/j.sca.2023.100024

Thi, H.-L., N. (2025). Harnessing the power of Big Data: transforming market prediction and supply chain optimization. HPU2 Journal of Science: Natural Sciences and Technology, 4(01), 71–83. https://doi.org/10.56764/hpu2.jos.2025.4.01.71-83

Yang, Y. (2024). A Dynamic Export Product Sales Forecasting Model Based on Controllable Relevance Big Data for Cross-Border E-Commerce. Applied Mathematics and Nonlinear Sciences, 9(1), 10. https://doi.org/10.2478/amns.2023.2.00049

Downloads

Published

2025-03-29

Issue

Section

Articles

How to Cite

Model Prediksi Permintaan Produk Berbasis Big Data Analytics untuk Pengendalian Persediaan Multi-Produk. (2025). Indonesian Journal of Engineering (IJE), 5(2), 94-109. https://doi.org/10.69503/ije.v5i2.1624

Most read articles by the same author(s)

<< < 1 2 3 4 5 6 > >>