ANALYSIS OF THE IMPACT OF SARS-COV-2 PANDEMIC PARAMETERS ON PHARMACEUTICAL COMPANY STOCK PRICES

Abstract

A company’s share price today is influenced by numerous factors, including internal fundamentals, political decisions, industry-specific developments, macroeconomic conditions, and global trends. Investors face the challenge of choosing an appropriate approach to identifying target industries and assets, interpreting analytical results, and determining optimal market entry points. One such challenge has been the COVID-19 pandemic. Within this context, key issues arise regarding the prediction of share price movements for companies in the healthcare sector (Pfizer Inc., BioNTech SE, Moderna Inc., Merck & Co Inc., GSK plc.) listed on the stock exchange. This study investigates the influence of COVID-19 case data, transformed through various technical indicators, on the accuracy of share price forecasts. It identifies the specific tasks these indicators address and proposes a systematic framework for selecting and configuring technical analysis tools. The paper explores different methods of generating and interpreting signals from individual indicators and their combinations, emphasizing their relevance to forecasting asset price movements. Several criteria are introduced for evaluating the effectiveness of these forecasting methods during the testing phase. The study compares the outcomes of different forecasting system configurations, identifying the most effective ones based on predefined criteria. Using weekly stock data from 2020 to 2024, the research establishes the optimal combination of indicators for the forecasting system. Furthermore, it highlights potential areas for optimization and suggests additional tools for enhancing system performance. In conclusion, the study demonstrates the feasibility of the proposed forecasting approach for conducting real stock transactions involving the selected healthcare companies’ shares. The practical value of the study lies in its demonstration that publicly available, non-financial data can be transformed into effective market forecasting tools. This has implications for investors, analysts, and portfolio managers seeking to enhance their decision-making frameworks during periods of global uncertainty. Moreover, the developed approach offers a flexible blueprint for adapting to future crises, where the speed of information processing and interpretation may determine the success of strategic financial decisions.