Comparative Evaluation of Statistical Models and Machine Learning Approaches in Modelling the Energy Dependency of the BIST Industrial Index: Balancing Predictive Performance and Interpretability
Journal Title: Journal of Corporate Governance, Insurance, and Risk Management - Year 2024, Vol 11, Issue 3
Abstract
Energy dependency plays a pivotal role in shaping the performance of stock markets, particularly in energy-sensitive indices such as the BIST Industrial Index in Turkey. This study presents a comparative evaluation of traditional statistical models and machine learning (ML) techniques in capturing the complex relationship between energy variables and the BIST Industrial Index. A dataset encompassing energy imports, production levels, and energy prices is utilised to assess the effectiveness of Ordinary Least Squares (OLS) regression, Random Forest (RF), and Gradient Boosting (GB) models. The results reveal that ML models substantially outperform traditional statistical methods in their ability to capture nonlinear, intricate relationships between energy metrics and market behaviour. Among the ML models, RF demonstrates the highest predictive accuracy. Feature importance analysis identifies crude oil production as the most significant variable, underscoring the dominant influence of domestic energy dynamics in shaping the BIST Industrial Index. While ML models offer superior forecasting capabilities, they introduce challenges in terms of model interpretability. In contexts where transparency is crucial, statistical models such as OLS remain more favoured for their simplicity and explainability. The findings highlight the need for a balanced approach in model selection, with hybrid models potentially offering the best of both worlds by combining the strengths of traditional and modern methodologies. The insights derived from this study can inform policymakers and investors, particularly within emerging markets, providing a nuanced understanding of the trade-offs between predictive power and model transparency in forecasting energy-sensitive financial indices.
Authors and Affiliations
Ahmet Akusta
Keywords
Related Articles
- EP ID EP754056
- DOI https://doi.org/10.56578/jcgirm110302
- Views 25
- Downloads 0
A View of the Future of the Metaverse Economy on the Basis of the Global Financial System: New Opportunities and Risks
The burgeoning Metaverse represents an unprecedented technology frontier that is poised to redefine our financial, societal, and cultural paradigms. This research introduces a new economic term, Metanomics, to the academ...
Performance Appraisal of Iron and Steel Enterprises Listed on BIST: An ENTROPY-Based TOPSIS Approach
The global iron and steel sector is currently navigating a period marked by significant volatility, driven by rising overcapacity and stagnating demand. In this challenging environment, businesses are increasingly compel...
The Impact of Managerial Sustainability and Ethics on Corporate Success
This investigation underscores the pivotal role of managerial sustainability and ethical practices in enhancing corporate success. Utilizing a comprehensive approach, the study amalgamates, interprets, and exemplifies pe...
Dynamics of High-Tech Investment and Export Growth in Turkey: A Multidisciplinary Analysis
This investigation delves into the dynamics of Turkey’s high-technology investments and their influence on export expansion. In an evolving global economy, the pivotal role of high technology industries for sustained eco...
Factors Affecting Health Insurance Adoption and Awareness in Uttar Pradesh, India: A Comprehensive Analysis
Objective: This study aims to investigate the significance of health insurance in the context of India's growing population, with a particular focus on Uttar Pradesh, the country's most populous state. By examining vario...