Do macroeconomic drivers fuel bubbles in emerging markets? Insights from GSADF and machine learning

Tetik, Metin (2026) Do macroeconomic drivers fuel bubbles in emerging markets? Insights from GSADF and machine learning. ACTA OECONOMICA, 76 (1). pp. 142-160. ISSN 0001-6373

Text 032-article-p142.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

This study analyzes speculative stock market bubbles in 17 emerging market indices (2005–2025) using the GSADF test for detection and Random Forest/logistic regression for driver identification. Bubble episodes are found in 7 indices, mainly from 2020 to 2025, reflecting market volatility in Turkey, India, China, Argentina, Taiwan, Hungary, and the Czech Republic. Random Forest models identify global equity trends (MSCIWorld) and risk aversion (GoldPrice, VIX) as key drivers, with commodity prices (BrentOil) playing a dominant role in Argentina. Logistic regression confirms these findings, highlighting MSCIWorld, GoldPrice, and VIX as significant factors in bubble-prone markets. A heatmap underscores the heterogeneity of bubble drivers, offering insights into emerging market dynamics. The study contributes to behavioral finance by examining global and local influences on bubbles and provides implications for policymakers and investors.

Actions (login required)

Edit Item