Demystifying the trend of the healthcare index: Is historical price a key driver?

TL;DR

This work investigates whether historical OHLC data can predict the next trading day's opening direction of healthcare indices using a one-step-ahead rolling classification framework. It introduces a novel nowcasting feature set based on mutual OHLC ratios, alongside volatility indicators, and demonstrates that these features are the strongest predictors across US and Indian markets (2019–2024), achieving accuracy above 0.8 and MCC above 0.6. Shapley-based explainability reveals that nowcasting features dominate model decisions, with intrinsic price signals offering additional, albeit smaller, contributions. The study emphasizes societal utility by enabling more transparent, equitable forecasting from publicly available data and discusses the implications for healthcare funding flows, market stability, and potential observer effects in deployment.

Abstract

Healthcare sector indices consolidate the economic health of pharmaceutical, biotechnology, and healthcare service firms. The short-term movements in these indices are closely intertwined with capital allocation decisions affecting research and development investment, drug availability, and long-term health outcomes. This research investigates whether historical open-high-low-close (OHLC) index data contain sufficient information for predicting the directional movement of the opening index on the subsequent trading day. The problem is formulated as a supervised classification task involving a one-step-ahead rolling window. A diverse feature set is constructed, comprising original prices, volatility-based technical indicators, and a novel class of nowcasting features derived from mutual OHLC ratios. The framework is evaluated on data from healthcare indices in the U.S. and Indian markets over a five-year period spanning multiple economic phases, including the COVID-19 pandemic. The results demonstrate robust predictive performance, with accuracy exceeding 0.8 and Matthews correlation coefficients above 0.6. Notably, the proposed nowcasting features have emerged as a key determinant of the market movement. We have employed the Shapley-based explainability paradigm to further elucidate the contribution of the features: outcomes reveal the dominant role of the nowcasting features, followed by a more moderate contribution of original prices. This research offers a societal utility: the proposed features and model for short-term forecasting of healthcare indices can reduce information asymmetry and support a more stable and equitable health economy.

Figures (6)

• Figure 7: The plots present the accuracy scores for the open-close across a feature-classifiers grid. Plots (a) and (b) are dedicated to S$\&$P 500 and BSE, respectively. The vertical axis shows different combinations of features, while the horizontal axis lists the classifiers. The higher the accuracy score, the better the performance. Consequently, larger circle radii and darker colors indicate better performance.
• Figure 8: The plots present the MCC scores for the open-close across a feature-classifiers grid. Plots (a) and (b) are dedicated to S$\&$P 500 and BSE, respectively. The vertical axis shows different combinations of features, while the horizontal axis lists the classifiers. The higher the MCC score, the better the performance. Consequently, larger circle radii and darker colors indicate better performance.
• Figure 9: Shapley values obtained in the task of predicting the next day's open index's rise or fall, relative to the current day's open index.
• Figure 10: Shapley values obtained in the task of predicting the next day's open index's rise or fall, relative to the current day's high index.
• Figure 11: Shapley values obtained in the task of predicting the next day's open index's rise or fall, relative to the current day's low index.