Sağlık Sektöründeki Finansal ve Psikolojik Dinamiklerin Tembel Öğrenme Algoritmaları ile Modellenmesi

The healthcare sector is highly sensitive to financial fluctuations and psychological factors. Notably, during crises like the COVID-19 pandemic, decision-makers in this sector must consider macroeconomic data and the crises' effects on financial markets. This study aims to assess the impact of psychological factors and market actors' expectations on the healthcare sector. In analyzing the determinants of the MSCI World Healthcare Index, psychologically based economic indicators, the MSCI Volatility Index, and the Consumer Confidence Index were utilized as independent variables. The impact of these psychological factors was modeled using the IBk, K-Star, and LWL algorithms from the lazy learning models. The analysis utilized daily data spanning from January 1, 2020, to September 30, 2024, a period marked by heightened uncertainty due to the COVID-19 pandemic. The decrease in the MSCI Healthcare Index was predicted with 95% accuracy using LWL, 86% with K-Star, and 68% with IBk. The increase was predicted with 23% accuracy using LWL, 35% with K-Star, and 50% with IBk. Performance and error analysis determined that the K-Star algorithm is the most effective method for evaluating the effects of psychological factors in the healthcare sector. The algorithms demonstrated low accuracy in the uptrend class but high accuracy in the downtrend class. This indicates that while the models are effective in predicting adverse market conditions, such as crises and crashes, their ability to accurately forecast positive market movements remains limited. The findings of the study emphasize the critical importance of considering psychological factors, such as volatility and the consumer confidence index, in making effective decisions in dynamic and crisis-sensitive markets, particularly in sectors like healthcare.