Asset Class Volatility and Output Gap in Africa: A Big Data Analysis

Abstract

This study investigates the relationship between asset class volatility and the output gap in selected African countries Nigeria, Ghana, Cameroon, and Côte d'Ivoire using machine learning techniques on daily financial data from 2010 to 2022. Employing advanced computational models, including Light Gradient Boosting Machine (LightGBM), the study achieves an R-squared of 0.68, demonstrating the effectiveness of big data analytics in economic research. The findings reveal that stock market volatility has the most significant impact on the output gap, followed by gold and crude oil, while Bitcoin exhibits the least influence. The study highlights the importance of stabilizing stock markets, leveraging gold as a financial hedge, managing crude oil price fluctuations, and regulating cryptocurrency markets to enhance macroeconomic stability. These insights provide valuable policy recommendations for mitigating financial volatility and ensuring sustainable economic growth in Africa. By integrating machine learning into economic research, the study offers a novel approach to understanding financial market dynamics and their implications for macroeconomic stability.

Received: 27 November 2024 | Revised: 12 March 2025 | Accepted: 28 March 2025

Conflicts of Interest

The author declares that he has no conflicts of interest in this work.

Data Availability Statement

The data that support this work are available upon reasonable request to the corresponding author.

Author Contribution Statement

Richard Umeokwobi: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing - original draft, Writing - review & editing, Visualization, Supervision, Project administration, Funding acquisition.