Assessing the Predictive Power of Country-Level Performance Indices on FinTech Firm Outcomes, Using Machine Learning Techniques

Tokat Y. E., Yilmaz G. N., Coita I. -. F.

5th International Conference on Informatics and Software Engineering, IISEC 2026, Ankara, Türkiye, 5 - 06 Şubat 2026, ss.578-583, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/iisec69317.2026.11418441
  • Basıldığı Şehir: Ankara
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.578-583
  • Anahtar Kelimeler: FinTech, machine learning, macroeconomic indicators, OLS regression, Random Forest
  • TED Üniversitesi Adresli: Evet

Özet

This study investigates whether a FinTech firm's economic performance index is influenced by key country-level indicators, namely Gross Domestic Product (GDP) growth, GDP per capita growth, consumer price inflation, foreign direct investment inflows, and domestic credit to the private sector. Firm-level performance data come from financial charts provided by Wroclaw University of Economics and Business, while macroeconomic variables are drawn from the World Bank Group's World Development Indicators and its Country and Loan Group income classifications. Using out-of-sample ordinary least squares regression and five-fold cross-validated random forests, the analysis consistently yields negative R2 values and low annual correlations, indicating no meaningful predictive link between the selected macro indices and FinTech firm performance. These robust null results challenge and refine earlier macro-FinTech studies, demonstrating that the assumed relationship between the examined country-level indicators and firm-level outcomes does not hold under the current data and methods.