Innovative models for forecasting demand for medicines in Ukraine using machine learning

Authors

  • Svitlana Fedenko Candidate of Economic Sciences, Associate Professor of the Department of Pharmaceutical Management, Drug Technology and Pharmacognosy of the Ivano-Frankivsk National Medical University, Ivano-Frankivsk, Ukraine https://orcid.org/0000-0001-7650-3569
  • Natela Dovzhuk Candidate of Pedagogical Sciences, Assistant Professor of the Department of Physiology of the Bogomolets National Medical University, Kyiv, Ukraine https://orcid.org/0000-0002-0468-9322
  • Liudmyla Konovalova Ph.D., Associate Professor of the Department of Pharmacy Organization and Economics of the Bogomolets National Medical University, Kyiv, Ukraine https://orcid.org/0000-0002-8956-1263

DOI:

https://doi.org/10.5281/zenodo.14927282

Keywords:

data analytics, predictive modelling, artificial intelligence, pharmaceutical market, economic efficiency

Abstract

Forecasting the demand for medicines is an important task to ensure the stable functioning of the pharmaceutical market, efficient inventory management and minimize the risk of drug shortages. In the context of economic and social instability, traditional forecasting methods are showing a decline in efficiency, which necessitates the introduction of innovative approaches, including machine learning algorithms. These methods allow to take into account the complex multifactorial nature of demand, which increases the accuracy of forecasting.

The purpose of the study is to analyze the existing developments and possibilities for implementing innovative models for forecasting demand for medicines in Ukraine using machine learning algorithms. Particular attention is paid to improving the accuracy of forecasts in the context of dynamic market conditions and supply chain variables.

The study is based on theoretical analysis and systematization of scientific sources from PubMed and Google Scholar databases (for the last 5 years). Data was collected and processed taking into account the specifics of the Ukrainian pharmaceutical market. The method of generalization was used to present a comprehensive assessment of the effectiveness and prospects for the introduction of the latest technologies in the industry.

The results of the study show that the use of innovative forecasting models demonstrates significantly higher accuracy compared to traditional statistical methods. The use of machine learning algorithms makes it possible to identify hidden patterns of demand, optimize inventory management, reduce the risk of shortages, and cut costs in supply chains. The results also show that the effectiveness of modern technologies, especially in crisis situations, far exceeds the capabilities of classical approaches.

The conclusions summarize that the introduction of machine learning methods in the forecasting of demand for medicines has significant potential for transforming the pharmaceutical sector in Ukraine. The integration of intelligent technologies into management systems will ensure stable access to essential medicines for the population, increase the efficiency of logistics processes, and adapt the market to conditions of increased uncertainty.

Published

2025-02-25

How to Cite

Fedenko, S., Dovzhuk, N., & Konovalova, L. (2025). Innovative models for forecasting demand for medicines in Ukraine using machine learning. Achievements of the Economy: Prospects and Innovations, (15). https://doi.org/10.5281/zenodo.14927282