Techniques for Predicting Pharmaceutical Demand Using Machine Learning

This        comprehensive       review       and bibliometric      assessment      emphasize the increasing significance of ML in predicting pharmaceutical demand, especially in tackling the issues associated with demand variability, stock optimization, and supply network endurance. The research shows that sophisticated ML models such LR, LSTM, RF, ANN, and XGBoost provide enhanced performance in contrast to conventional statistical techniques, like linear regression, particularly in modelling intricate, nonlinear demand designs. Bibliometric mapping additionally demonstrates the evolution of studies, incorporating terms like "LR," "supply "management of supply chains," and "sustainable practices" coming to the forefront as predominant patterns in the domain. The combination of ML with technologies like blockchain and ERP systems indicates a transformational move towards information-based, smart pharmaceutical logistics that enhance operational efficiency effectiveness while also improving patient results.   This paper adds to the current pool of understanding through the integration of methodological understanding and bibliometric patterns, providing a thorough insight of ML techniques are utilized and assessed in pharmaceuticals forecasting demand. It also recognizes significant deficiencies in the present research, including the necessity for hybrid models, the incorporation of practical data, and the requirement for greater clarity intricate algorithms. The results highlight the strategic importance of ML in healthcare strategy, indicating that future studies to concentrate on creating scalable, clear and context-sensitive prediction systems.   Additionally, the majority of the examined studies are hindered by insufficient data and absence of practical applications validation, restricting the applicability of the suggested models. Intricate algorithms like LSTM and XGBoost, despite their strength, frequently lack  clarity,  creating  difficulties for adherence to regulations and confidence from stakeholders. Prospects research must focus on creating interpretable ML frameworks, utilizing synthetic or federated data to tackle concerns regarding privacy and availability, along with implementing predictive models utilizing real-time supply chain systems for dynamic enablement decision-making in uncertain conditions.   REFERENCES 

1.        Kumari, A., Bohra, N. (2021). Prediction of drug sales by using neural network algorithm. In The 2nd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2020, 32.                https://doi.org/10.4108/eai.27-2- 2020.2303124 2.        Mbonyinshuti, F., Nkurunziza, J., Niyobuhungiro, J., Kayitare, E. (2024). Health supply chain forecasting: A comparison of ARIMA and LSTM time series models for demand prediction of medicines. Acta Logistica, 11(2): 269-280. https://doi.org/10.22306/al.v11i2.510 3.        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 4.        Matha, R., Mukherjee, S., Panigrahi, R.R., Shrivastava, A.K. (2025). A bibliometric analysis of Industry 5.0 and healthcare supply chain research: Emerging opportunities and future challenges. Supply  Chain  Analytics,  10:  100125. https://doi.org/10.1016/j.sca.2025.10012 5 5.        Adeleke, D.A., Samuel, A.D. (2024). Optimizing pharmaceutical supply chain management through AI driven predictive analytics: A conceptual framework. Computer Science, 5(11): 2580-2593. https://doi.org/10.51594/csitrj.v5i11.170 9 6.        Vashishtha, S. (2025). Impact of machine learning on drug demand forecasting in pharmaceutical                  supply          chains. International Journal of Research in all Subjects in Multi Languages (IJRSML), 14(4):   29-37. https://doi.org/10.63345/ijrsml.v13.i4.4 7.        Guo, W. (2023). Exploring the value of AI technology in optimizing and implementing supply chain data for pharmaceutical companies. Innovation in Science and Technology, 2(3): https://doi.org/10.56397/ist.2023.05.01 8.        Chen, J. (2024). Advanced analytics for retail inventory and demand forecasting. Transactions on Economics, Business and Management Research, 10: 113-119. https://doi.org/10.62051/jme9b319 9.        Aljohani, A. (2023). Predictive analytics and machine learning for real-time supply chain risk mitigation and agility. Sustainability,           15(20): https://doi.org/10.3390/su152015088 10.     Batubara, A.S.B.A.S., Dafitri, H., Faisal, I. (2022). Analysis of linear regression and trend moment methods in predicting sales using MAPE. Jurnal Sistem Informasi dan Ilmu   Komputer,   6(1):   75-81. https://doi.org/10.34012/jurnalsisteminfo rmasidanilmuk omputer.v6i1.2919