Марковски превключващ мултифрактален модел: симулиране на рисковия профил на българския финансов пазар
Markov Switching Multifractal Model: Simulating the Risk Profile of the Bulgarian Financial Market

Author(s): Petar Rangelov
Subject(s): Economy, National Economy, Financial Markets, Socio-Economic Research
Published by: Университет за национално и световно стопанство (УНСС)
Keywords: multifractal model
Summary/Abstract: The publication is a continuation of the article "Application of Fractal Geometry in Studies of the Bulgarian Financial Market", included in issue 2 of 2023 of the "Economic and Social Alternatives" journal. In this study, the main concepts resulting from the application of fractal geometry aimed at describing the dynamics of financial markets and in particular, the main Bulgarian stock market index SOFIX, were demonstrated. The current study builds on the application of fractal analysis in the field of the Bulgarian financial market and for this purpose one of the leading fractal models is presented – the continuous binomial Markov Switching Multifractal Model. A diagnostic comparative analysis of the ability to fit the real data between the selected fractal model and a control group of leading econometric models from the family of the autoregressive conditional heteroscedasticity was made. In conclusion, a simulated reconstruction of the returns of price trajectories produced by the multifractal model was performed, and it can be clearly seen that the simulated returns mimic extremely accurately the real observed data and risk profile of the index.

• Details
• Contents