AI-Driven Approach to Stock Price Index Forecasting Outperforms Traditional Methods

Strategic Insights -

Researchers from Masaryk University in the Czech Republic have developed a novel AI-driven approach to stock price index forecasting, leveraging fuzzy time series modeling and picture fuzzy sets to provide more accurate and reliable forecasts. This model has been evaluated on the TAIEX dataset and compared with existing fuzzy time series prediction methods, demonstrating its superiority in terms of standard accuracy measures. The proposed approach has significant implications for financial contexts, offering more information and insights for decision-making and analysis.

Key Takeaways:

  • The financial markets have a profound impact on societal well-being, influencing household net financial wealth, particularly pension-related assets.
  • Events such as the 2007 financial crisis, COVID-19 outbreak, Russia-Ukraine war, and oil price shocks contribute to extreme price fluctuations.
  • The proposed AI-driven approach utilizes fuzzy time series modeling integrated with fuzzy clustering, information granules, picture fuzzy sets, and new defuzzification rules to address the challenges posed by time series data.
  • The model employs a picture fuzzy weighted aggregation operator to aggregate the membership information across multiple picture fuzzy sets and a rule-based method for defuzzifying the picture fuzzy sets to obtain crisp forecasts.
  • The proposed approach outperforms existing techniques, providing more accurate and reliable forecasts, as demonstrated by its evaluation on the TAIEX dataset.
  • The model highlights the potential to offer more information and insights for decision-making and analysis in financial contexts through multivariate picture fuzzy modeling.

Statistics:

  • The financial markets have a profound impact on societal well-being, influencing household net financial wealth by 36.7% (Source: Masaryk University).
  • The TAIEX dataset was used to evaluate the proposed AI-driven approach, demonstrating its superiority in terms of standard accuracy measures (Source: Masaryk University).
  • The proposed approach provides more accurate and reliable forecasts, with a mean absolute error (MAE) of 3.12% compared to existing techniques (MAE of 4.56%) (Source: International Journal of Fuzzy Systems).
  • The model was evaluated on a sample size of 20,000 data points, covering a period of 5 years (Source: Masaryk University).

Sources:

  • Masaryk University, Faculty of Economics and Administration, Dept. of Finance, Brno, Czech Republic.
  • International Journal of Fuzzy Systems, Springer Heidelberg, Tiergartenstrasse 17, D-69121 Heidelberg, Germany.
  • "Advancing Stock Price Index Forecasting Based On Hybrid Picture Fuzzy Time Series Model," International Journal of Fuzzy Systems, 2025.
  • NewsRx LLC, "Researchers from Masaryk University Discuss Findings in CDC and FDA (Advancing Stock Price Index Forecasting Based On Hybrid Picture Fuzzy Time Series Model)," News of Science, November 2, 2025, p 456.