arbiter
JournalsPricingAccount

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

Metin TETİK

Acta Oeconomica2026https://doi.org/10.1556/032.2026.00177article
ABDC C
Weight
0.50

What the paper says

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.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1556/032.2026.00177

Or copy a formatted citation

@article{metin2026,
  title        = {{Do macroeconomic drivers fuel bubbles in emerging markets? Insights from GSADF and machine learning}},
  author       = {Metin TETİK},
  journal      = {Acta Oeconomica},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1556/032.2026.00177},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

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

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.