Skip to content
2000
image of Demand Forecasting in the Tunisian Pharmaceutical Industry: A Comparative Study

Abstract

Introduction

Demand forecasting is critical for the pharmaceutical industry to ensure efficient production, inventory management, and distribution, especially in dynamic and competitive markets. This study addresses the challenges of accurate demand prediction within the Tunisian pharmaceutical sector.

Methods

The primary aim was to compare the forecasting accuracy of two methods, Holt-Winters (HW) and Multilayer Perceptron (MLP) neural networks, for three drug categories: Antiviral, Antibiotic, and Pain Relief. Additionally, the study provides actionable recommendations to enhance forecasting strategies. A 24-month (n=24) historical sales dataset (October 2020 to September 2022) from a Tunisian pharmaceutical demand forecasting company was analyzed. The analysis utilized the Holt-Winters model to incorporate seasonal adjustments and an MLP neural network to capture complex, non-linear sales patterns.

Results

Both models were evaluated using metrics such as mean squared error (MSE) to quantify prediction accuracy. The MLP neural network consistently and significantly outperformed the Holt-Winters method, demonstrating markedly lower MSE values (., 0.0206 for Antivirals, compared to 30.06 for HW) and greater adaptability to demand variability across all drug categories.

Discussion

While effective for seasonal patterns, HW struggled with irregular fluctuations and complex dynamics. This study highlights the superiority of MLP neural networks for pharmaceutical demand forecasting due to their adaptability and accuracy in handling non-linear and variable data.

Conclusion

The findings provide a strong quantitative basis for Tunisian pharmaceutical companies to adopt advanced machine learning techniques for more reliable planning, 
potentially leading to the development of proprietary, patentable forecasting systems. However, to fully realize the potential of these techniques and address the limitations outlined in this research, future research should explore hybrid models and integrate 
extended datasets that incorporate external market dynamics and trends.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/biot/10.2174/0118722083394111250929111803
2025-10-09
2025-11-07

  • From This Site

    /content/journals/biot/10.2174/0118722083394111250929111803
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Alzoubi H.M. Alshurideh M.T. Nuseir M.T. Al Kurdi B. AlHamad A. Hamadneh S. The impact of demand forecasting on effective supply chain with mediating role of strategic planning in the UAE pharmaceutical industry. Studies in Big Data 2024 117 561 581 10.1007/978‑3‑031‑31801‑6_33
    [Google Scholar]
  2. Ayed Lakhal D. Bel Hadj Kacem S. Tagina M. Amara M.A. A hybrid approach for the sales forecasting of paracetamol products. J Artif Intell Technol 2024 4 4 296 304 10.37965/jait.2024.0572
    [Google Scholar]
  3. Azmat M Siddiqui R Enhancing supply chain efficiency: A holistic examination of hybrid forecasting models employing mode and PERT technique as deterministic factors. Int J Logist Res Appl 2023 1 19 10.1080/13675567.2023.2280094
    [Google Scholar]
  4. Belghith M. Ben Ammar H. Elloumi A. Hachicha W. A new rolling forecasting framework using Microsoft Power BI for data visualization: A case study in a pharmaceutical industry. Ann. Pharm. Fr. 2024 82 3 493 506 10.1016/j.pharma.2023.10.013 37925145
    [Google Scholar]
  5. Elkourchi A. El Oualidi M.A. Ahlaqqach M. Demand forecast of pharmaceutical products during COVID-19 using Holt-Winters exponential smoothing. Lect Notes Netw Syst 2023 772 427 437 10.1007/978‑3‑031‑43520‑1_36
    [Google Scholar]
  6. Fourkiotis K.P. Tsadiras A. Applying machine learning and statistical forecasting methods for enhancing pharmaceutical sales predictions. Forecasting 2024 6 1 170 186 10.3390/forecast6010010
    [Google Scholar]
  7. Albrakat O.J. Al-Gasawneh J.A. Al-Zoubi M.M. Pharmaceutical supply chain management in Jordan: Forecasting challenges and opportunities. Jordan J. Pharm. Sci. 2023 16 3 415 429
    [Google Scholar]
  8. Al-Shboul M.A. Modeling and forecasting pharmaceutical demand in the MENA region: An empirical analysis. J Supply Chain Manag Sci 2024 5 1 78 92
    [Google Scholar]
  9. Hamdi I. Toumi S. An ISM-MICMAC approach for analyzing the relationship between blockchain adoption criteria in a pharmaceutical supply chain: Tunisian case. J. Model. Manag. 2025 20 2 495 516 10.1108/JM2‑01‑2024‑0020
    [Google Scholar]
  10. Jahani M. Zojaji Z. Montazerolghaem A. Isfahan Artificial Intelligence event 2023: Drug demand forecasting. J. Med. Signals Sens. 2025 15 1 2 10.4103/jmss.jmss_59_24 40028044
    [Google Scholar]
  11. Nabli H. Ghannem A. Djemaa R.B. Sliman L. How innovative technologies shape the future of pharmaceutical supply chains. Comput. Ind. Eng. 2025 199 110745 10.1016/j.cie.2024.110745
    [Google Scholar]
  12. Pesqueira A. AI AI and ESG role in optimizing mRNA and protein-based vaccines supply chains from raw material sourcing to last-mile delivery Chim. Oggi 2024 42 6 6 9
    [Google Scholar]
  13. Sakthi Ganesh Dharani R. Lokheshram S.V. Malini A. Seasonal disease-based demand forecasting for pharmaceutical medications using Random Forest. Lect Notes Comput Sci 2023 13924 261 268 10.1007/978‑3‑031‑44084‑7_25
    [Google Scholar]
  14. Yani L.P.E. Aamer A. Demand forecasting accuracy in the pharmaceutical supply chain: A machine learning approach. Int. J. Pharm. Healthc. Mark. 2023 17 1 1 23 10.1108/IJPHM‑05‑2021‑0056
    [Google Scholar]
  15. Clark J. Brown D. Pharmaceutical supply chain optimization: The role of predictive analytics in managing demand. Int J Supply Chain Manag 2020 25 3 188 197 10.1016/j.ijscm.2020.02.007
    [Google Scholar]
  16. Wang Z. Chen L. Forecasting pharmaceutical demand with multilayer perceptron neural networks. Comput. Ind. Eng. 2021 135 124 136 10.1016/j.cie.2021.01.021
    [Google Scholar]
  17. Gupta S. Kumar R. Impact of the bullwhip effect on pharmaceutical supply chains. J. Bus. Logist. 2020 41 1 55 66 10.1002/jbl.12145
    [Google Scholar]
  18. Smith J. Johnson R. Integrated forecasting for pharmaceutical supply chains: A critical review. Int. J. Forecast. 2020 35 3 212 225 10.1016/j.ijforecast.2020.01.005
    [Google Scholar]
  19. Liu R. Vakharia V. Optimizing supply chain management through BO-CNN-LSTM for demand forecasting and inventory management. J. Organ. End User Comput. 2024 36 1 1 25 10.4018/JOEUC.335591
    [Google Scholar]
  20. Zhang T. Wang J. Time series forecasting using Holt-Winters method for pharmaceutical demand prediction. Comput. Ind. Eng. 2019 142 56 67 10.1016/j.cie.2019.05.016
    [Google Scholar]
  21. Carter S. Lee P. Artificial intelligence applications in pharmaceutical demand forecasting: A review. Comput. Ind. Eng. 2020 151 102 115 10.1016/j.cie.2020.05.017
    [Google Scholar]
  22. Azadi M. Yousefi S. Farzipoor Saen R. Shabanpour H. Jabeen F. Forecasting sustainability of healthcare supply chains using deep learning and network data envelopment analysis. J. Bus. Res. 2023 154 113357 10.1016/j.jbusres.2022.113357
    [Google Scholar]
  23. Long P. Lu L. Chen Q. Chen Y. Li C. Luo X. Intelligent selection of healthcare supply chain mode – An applied research based on artificial intelligence. Front. Public Health 2023 11 1310016 10.3389/fpubh.2023.1310016 38164449
    [Google Scholar]
  24. Painuly S. Sharma S. Matta P. Deep learning tools and techniques in e-healthcare supply chain management system. Proceedings of the 2023 IEEE 8th International Conference for Convergence in Technology (I2CT). Lonavla, India, 07-09 April 2023 1 6 10.1109/I2CT57861.2023.10126339
    [Google Scholar]
  25. Hooshmand Pakdel A. Abbasi M. Farrokhi M. A hybrid ARIMA-LSTM model for enhanced pharmaceutical demand forecasting in volatile markets. Int. J. Forecast. 2025 41 2 215 228
    [Google Scholar]
  26. Nguyen T.H. Tran V.Q. Le D.M. Deep Learning approaches for pharmaceutical sales prediction: A comparative study of LSTM and gated recurrent unit networks. Expert Syst. Appl. 2025 245 118934
    [Google Scholar]
  27. Zhang Q. Liu J. Comparative study of traditional and machine learning models in pharmaceutical demand forecasting. Int. J. Pharma Sci. 2020 12 5 123 135 10.1016/j.ijps.2020.05.008
    [Google Scholar]
  28. Cai J. Sharkawi I. Taasim S.I. The role of Deep Learning in supply chain collaboration and cooperation. J. Organ. End User Comput. 2024 36 1 1 23 10.4018/JOEUC.342841
    [Google Scholar]
  29. Nguyen H.D. Tran K.P. Thomassey S. Hamad M. Forecasting and anomaly detection approaches using LSTM and LSTM autoencoder techniques with the applications in supply chain management. Int. J. Inf. Manage. 2021 57 102282 10.1016/j.ijinfomgt.2020.102282
    [Google Scholar]
  30. Koushik P. Mittal S. Jain S.N. Whig P. Quantum computing and supply chain management: A new era of optimization. Enhancing predictive maintenance in supply chain systems with deep learning strategies. Hershey, PA IGI Global 2024 141 159
    [Google Scholar]
  31. Tahir B. Tariq M. Federated learning for supply chain management 5.0. Federated learning for multimedia data processing and security in industry 50. Stevenage, UK: The Institution of Engineering and Technology 2025 181 201 10.1049/PBPC066E_ch9
    [Google Scholar]
  32. Aljohani A. Predictive analytics and machine learning for real-time supply chain risk mitigation and agility. Sustainability 2023 15 20 15088 10.3390/su152015088
    [Google Scholar]
  33. Côté M-C Duplessis F Todosic A Supply chain forecasting system. Patent US2021374632A1 2021
    [Google Scholar]
  34. Belghith M. Bouajaja S. Implementation of an advanced planning and scheduling system in a pharmaceutical context. Ann. Pharm. Fr. 2024 82 3 584 595 10.1016/j.pharma.2024.02.007 38367935
    [Google Scholar]
  35. Huang A. Zhuang J. Ren Y. Rao Y. Tsai S. Supply chain management in the digital economy. J. Glob. Inf. Manage. 2024 32 1 1 27 10.4018/JGIM.361589
    [Google Scholar]
/content/journals/biot/10.2174/0118722083394111250929111803
Loading
Demand Forecasting in the Tunisian Pharmaceutical Industry: A Comparative Study
Bentham Science Publishers ; https://doi.org/10.2174/0118722083394111250929111803
/content/journals/biot/10.2174/0118722083394111250929111803
/content/journals/biot/10.2174/0118722083394111250929111803
Loading

Data & Media loading...


  • Article Type:     Research Article
Keywords: artificial intelligence ; multilayer perceptron ; comparative analysis ; pharmaceutical industry ; Demand forecasting ; holt-winters method

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test