Comparative Analysis of Machine Learning and Artificial Intelligence Algorithms for Pharmaceutical Demand Forecasting in Hospital Supply Chains: A Case Study at Hospital X
Abstract
Healthcare systems in Indonesia face unique challenges due to diverse geographical landscapes and high dependency on pharmaceutical imports, resulting in complex demand forecasting requirements. This study proposes an innovative approach to pharmaceutical demand forecasting by leveraging Machine Learning (ML) and Artificial Intelligence (AI) techniques to optimize hospital supply chains. A comparative evaluation of six forecasting algorithms was conducted using 650 days of pharmaceutical transaction data from Hospital X, encompassing 374,171 dispensing events. The study compared traditional time series methods (Simple Moving Average, Weighted Moving Average, Exponential Smoothing) with advanced ML algorithms (Linear Regression, Support Vector Regression, Deep Learning LSTM). Results demonstrate that the Deep Learning model achieved superior performance with MAPE of 2.35%, representing a 34.4% improvement over traditional methods. The integrated feature engineering architecture successfully captured temporal and seasonal patterns specific to tropical healthcare environments. Implementation of the ML-based forecasting system shows potential for 25-30% reduction in safety stock requirements while maintaining 99.5% service levels, translating to significant cost savings and improved drug availability in Indonesian hospital settings
Keywords:
Artificial intelligence, Demand forecasting, Machine learning, Hospital optimization, Pharmaceutical supply chain
Abstrak
Sistem pelayanan kesehatan di Indonesia menghadapi tantangan kompleks yang dipengaruhi oleh kondisi geografis yang beragam serta tingginya ketergantungan terhadap impor produk farmasi. Hal ini berdampak langsung pada kompleksitas dalam proses peramalan permintaan obat di rumah sakit. Penelitian ini mengusulkan pendekatan inovatif dalam peramalan permintaan farmasi dengan memanfaatkan teknik Machine Learning (ML) dan Artificial Intelligence (AI) guna mengoptimalkan rantai pasok rumah sakit. Evaluasi komparatif terhadap enam algoritma peramalan dilakukan menggunakan data transaksi farmasi selama 650 hari dari Rumah Sakit X, yang mencakup 374.171 data pemberian obat.Metode yang dibandingkan mencakup pendekatan deret waktu konvensional (Simple Moving Average, Weighted Moving Average, dan Exponential Smoothing) serta algoritma pembelajaran mesin tingkat lanjut (Regresi Linier, Support Vector Regression, dan Long Short-Term Memory atau LSTM). Hasil penelitian menunjukkan bahwa model Deep Learning LSTM menghasilkan performa terbaik dengan nilai Mean Absolute Percentage Error (MAPE) sebesar 2,35%, atau meningkat 34,4% dibandingkan dengan metode konvensional. Arsitektur rekayasa fitur yang digunakan mampu mengidentifikasi pola musiman dan temporal yang khas di lingkungan kesehatan tropis. Implementasi sistem peramalan berbasis ML ini menunjukkan potensi pengurangan kebutuhan safety stock sebesar 25–30%, dengan tetap mempertahankan tingkat layanan sebesar 99,5%. Temuan ini menunjukkan peluang penghematan biaya yang signifikan dan peningkatan ketersediaan obat di rumah sakit Indonesia.
Kata Kunci:
Kecerdasan buatan, Peramalan permintaan, Pembelajaran mesin, Optimasi rumah sakit, Rantai pasok farmasi
Keywords
Full Text:
PDFReferences
Abbasimehr, H., Shabani, M., & Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers & Industrial Engineering, 143, 106435. https://doi.org/10.1016/j.cie.2020.106435
Ahmad, M., Li, Q., & Wang, Z. (2025). LSTM-Transformer hybrid models for enhanced pharmaceutical demand forecasting. Neural Computing and Applications, 37(8), 1945-1962. https://doi.org/10.1007/s00521-025-07889-9
Al-Banna, A., Rana, Z. A., Yaqot, M., & Menezes, B. (2023). Interconnectedness between supply chain resilience, industry 4.0, and investment. Logistics, 7(3), 50. https://doi.org/10.3390/logistics7030050
Aljohani, A. (2023). Predictive analytics and machine learning for real-time supply chain risk mitigation and agility. Sustainability, 15(20), 15088. https://doi.org/10.3390/su152015088
Alshurideh, M. T., Hamadneh, S., Alzoubi, H. M., Al Kurdi, B., Nuseir, M. T., & Al Hamad, A. (2024). Empowering supply chain management system with machine learning and blockchain technology. In Cyber security impact on digitalization and business intelligence: Big cyber security for information management: Opportunities and challenges (pp. 335-349). Springer.
Atadoga, A., Osasona, F., Amoo, O. O., Farayola, O. A., Ayinla, B. S., & Abrahams, T. O. (2024). The role of IT in enhancing supply chain resilience: A global review. International Journal of Supply Chain Management, 13(2), 45-67.
Azadi, M., Yousefi, S., Saen, R. F., Shabanpour, H., & Jabeen, F. (2023). Forecasting sustainability of healthcare supply chains using deep learning and network data envelopment analysis. Journal of Business Research, 154, 113357. https://doi.org/10.1016/j.jbusres.2022.113357
Bandara, K., Shi, P., Bergmeir, C., Hewamalage, H., Tran, Q., & Seaman, B. (2019). Sales demand forecast in e-commerce using a long short-term memory neural network methodology. In Neural information processing (pp. 462-474). Springer.
Camur, M. C., Ravi, S. K., & Saleh, S. (2024). Enhancing supply chain resilience: A machine learning approach for predicting product availability dates under disruption. Expert Systems with Applications, 247, 123226. https://doi.org/10.1016/j.eswa.2024.123226
Chaudhuri, K., & Alkan, B. (2022). A hybrid extreme learning machine model with harris hawks optimisation algorithm: An optimised model for product demand forecasting applications. Applied Intelligence, 52(10), 11489-11505. https://doi.org/10.1007/s10489-022-03251-7
Chen, Y., Xie, X., Pei, Z., Yi, W., Wang, C., Zhang, W., & Ji, Z. (2024). Development of a time series e-commerce sales prediction method for short-shelf-life products using GRU-LightGBM. Applied Sciences, 14(2), 866. https://doi.org/10.3390/app14020866
Controlant. (2024). Trends for 2024: Pharma supply chain challenges and opportunities. Retrieved from https://www.controlant.com/insights/trends-for-2024-pharma-supply-chain-challenges-and-opportunities
Detwal, P. K., Soni, G., Jakhar, S. K., Shrivastava, D. K., Madaan, J., & Kayikci, Y. (2023). Machine learning-based technique for predicting vendor incoterm (contract) in global omnichannel pharmaceutical supply chain. Journal of Business Research, 158, 113688. https://doi.org/10.1016/j.jbusres.2022.113688
Faridi, S., Zaj, M. M., Daneshvar, A., Shahverdiani, S., & Roodposhti, F. R. (2023). Portfolio rebalancing based on a combined method of ensemble machine learning and genetic algorithm. Journal of Financial Reporting and Accounting, 21(1), 105-125. https://doi.org/10.1108/JFRA-06-2021-0150
Fitch Solutions. (2025). Government support will enhance Indonesia's pharmaceutical manufacturing despite challenges. Retrieved from https://www.fitchsolutions.com/bmi/pharmaceuticals/government-support-will-enhance-indonesias-pharmaceutical-manufacturing-despite-challenges-17-01-2025
Fourkiotis, K. P., & Tsadiras, A. (2024). Applying machine learning and statistical forecasting methods for enhancing pharmaceutical sales predictions. Forecasting, 6(1), 170-186. https://doi.org/10.3390/forecast6010010
Harvey, D., Leybourne, S., & Newbold, P. (1997). Testing the equality of prediction mean squared errors. International Journal of Forecasting, 13(2), 281-291. https://doi.org/10.1016/S0169-2070(96)00719-4
Hassan, J., Safiya, M. S., Deka, L., Uddin, M. J., & Das, D. B. (2024). Applications of machine learning (ML) and mathematical modeling (MM) in healthcare with special focus on cancer prognosis and anticancer therapy: Current status and challenges. Pharmaceutics, 16(2), 260. https://doi.org/10.3390/pharmaceutics16020260
Hupman, A., Tran, H. T., Schaefer, C., Menzer, C., Ghate, A., Taaffe, K., & Delman, B. (2024). Predicting pharmaceutical supply chain disruptions before and during the COVID-19 pandemic. Risk Analysis, 44(3), 567-584. https://doi.org/10.1111/risa.17453
Jahin, M. A., Shovon, M. S. H., Shin, J., Ridoy, I. A., & Mridha, M. F. (2024). Big data—supply chain management framework for forecasting: Data preprocessing and machine learning techniques. Archives of Computational Methods in Engineering, 31(4), 2435-2461. https://doi.org/10.1007/s11831-023-10040-5
Kumar, A., Mani, V., Jain, V., Gupta, H., & Venkatesh, V. G. (2023). Managing healthcare supply chain through artificial intelligence (AI): A study of critical success factors. Computers & Industrial Engineering, 175, 108815. https://doi.org/10.1016/j.cie.2022.108815
Kumar, A., Venkatesh, V. G., Mani, V., Jain, V., & Gupta, H. (2024). Digging DEEP: Futuristic building blocks of omni-channel healthcare supply chains resiliency using machine learning approach. Journal of Business Research, 162, 113903. https://doi.org/10.1016/j.jbusres.2023.113903
Merkuryeva, G., Valberga, A., & Smirnov, A. (2019). Demand forecasting in pharmaceutical supply chains: A case study. Procedia Computer Science, 149, 3-10. https://doi.org/10.1016/j.procs.2019.01.100
Nalendra, A.K., Mujiono, M., Akhsani, R., & Wahyu, A.S., (2020). Implementasi algoritma k-mean dalam pengelompokan data kecelakaan (studi kasus kabupaten kediri). VOCATECH: Vocational Education and Technology Journal, Vol. 2 (1), 52-60
Pasupuleti, V., Thuraka, B., Kodete, C. S., & Malisetty, S. (2024). Enhancing supply chain agility and sustainability through machine learning: Optimization techniques for logistics and inventory management. Logistics, 8(3), 73. https://doi.org/10.3390/logistics8030073
Rathipriya, R., Abdul Rahman, A. A., Dhamodharavadhani, S., Meero, A., & Yoganandan, G. (2023). Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model. Neural Computing and Applications, 35(2), 1945-1957. https://doi.org/10.1007/s00521-022-07889-9
Siddiqui, R., Azmat, M., Ahmed, S., & Kummer, S. (2021). A hybrid demand forecasting model for greater forecasting accuracy: The case of the pharmaceutical industry. Supply Chain Forum: An International Journal, 22(4), 323-341. https://doi.org/10.1080/16258312.2021.1967081
Tas, I., Satoglu, S.I. (2023). Demand Forecasting in Pharmaceutical Industry Under Covid-19 Pandemic Conditions by Machine Learning and Time Series Analysis. In: Kahraman, C., Sari, I.U., Oztaysi, B., Cebi, S., Cevik Onar, S., Tolga, A.Ç. (eds) Intelligent and Fuzzy Systems. INFUS 2023. Lecture Notes in Networks and Systems, vol 759. Springer, Cham. https://doi.org/10.1007/978-3-031-39777-6_19
Yani, L. P. E., & Aamer, A. (2023). Demand forecasting accuracy in the pharmaceutical supply chain: A machine learning approach. International Journal of Pharmaceutical and Healthcare Marketing, 17(1), 23-45. https://doi.org/10.1108/IJPHM-05-2021-0056
Zhang, B., Tan, W., Cai, W., & Zhang, A. (2022). Forecasting with visibility using privacy preserving federated learning. In Proceedings of the Winter Simulation Conference (pp. 2687-2698). IEEE Press. https://doi.org/10.1109/WSC55014.2022.9754156
Zhu, X., Ninh, A., Zhao, H., & Liu, Z. (2021). Demand forecasting with supply‐chain information and machine learning: Evidence in the pharmaceutical industry. Production and Operations Management, 30(9), 3231-3252. https://doi.org/10.1111/poms.13426
DOI: https://doi.org/10.38038/vocatech.v7i1.218
Refbacks
VOCATECH : Vocational and Technology Journal
Unit Penelitian dan Pengabdian Masyarakat & Penjaminan Mutu
Akademi Komunitas Negeri Aceh Barat
Komplek STTU Alue Peunyareng, Ujong Tanoh Darat, Meureubo, Kabupaten Aceh Barat, Aceh 23615
Telp. (0655) 7110271
Email: vocatech@aknacehbarat.ac.id
VOCATECH: Vocational Education and Technology Journal Published by:
Unit Penelitian dan Pengabdian Masyarakat & Penjaminan Mutu
Akademi Komunitas Negeri Aceh Barat
Indexed by:
VOCATECH: Vocational Education and Technology Journal Creative Commons Attribution-ShareAlike 4.0 International License.