<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>To reduce investment risk in financial markets, how to select effective factors and determine factor weights to construct an effective portfolio is the focus of current research. In this paper, we build a multi-factor quantitative model and explore the long-term equilibrium relationship and short-term volatility impact relationship of investment risk in financial markets with the help of econometric models and the impulse response analysis of the dynamic correlation of risk. Johansen cointegration test and error correction model are used for the analysis to examine the long-term equilibrium relationship and short-term volatility impact of financial market risk. Secondly, the correlations and influencing factors among the risks in each market under the financial market are explored by simple correlation coefficient analysis and the Granger causality test. Finally, the dynamic correlation of risk is examined by impulse response analysis. The results of the study show that the accuracy of similarity-weighted voting portfolio forecasts are all the highest, and their accuracy rates are 93.2%, 95.7%, and 96.8% in years (t-1) to (t-3), which are above 90%, respectively. The method in this paper can better detect the risky situations that are likely to occur in the next three years for financial market investments and identify them with superior results.</p>
</abstract>

To reduce investment risk in financial markets, how to select effective factors and determine factor weights to construct an effective portfolio is the focus of current research. In this paper, we build a multi-factor quantitative model and explore the long-term equilibrium relationship and short-term volatility impact relationship of investment risk in financial markets with the help of econometric models and the impulse response analysis of the dynamic correlation of risk. Johansen cointegration test and error correction model are used for the analysis to examine the long-term equilibrium relationship and short-term volatility impact of financial market risk. Secondly, the correlations and influencing factors among the risks in each market under the financial market are explored by simple correlation coefficient analysis and the Granger causality test. Finally, the dynamic correlation of risk is examined by impulse response analysis. The results of the study show that the accuracy of similarity-weighted voting portfolio forecasts are all the highest, and their accuracy rates are 93.2%, 95.7%, and 96.8% in years (t-1) to (t-3), which are above 90%, respectively. The method in this paper can better detect the risky situations that are likely to occur in the next three years for financial market investments and identify them with superior results.

Dynamic prediction of portfolio riskiness in financial markets based on multi-factor quantitative models

Shanghai University of Finance and Economics

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

To reduce investment risk in financial markets, how to select effective factors and determine factor weights to construct an effective portfolio is the focus...

Dynamic prediction of portfolio riskiness in financial markets based on multi-factor quantitative models

Data publikacji: 20 cze 2024

Zakres stron: -

Otrzymano: 08 kwi 2022

Przyjęty: 20 wrz 2022

DOI: https://doi.org/10.2478/amns-2024-1825

Słowa kluczowe
Multi-factor quantitative models, Financial markets, Portfolios, Granger causality, Riskiness dynamic forecasting

© 2024 Wei Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Dynamic prediction of portfolio riskiness in financial markets based on multi-factor quantitative models

Data publikacji: 20 cze 2024

Zakres stron: -

Otrzymano: 08 kwi 2022

Przyjęty: 20 wrz 2022

DOI: https://doi.org/10.2478/amns-2024-1825

Słowa kluczoweMulti-factor quantitative models, Financial markets, Portfolios, Granger causality, Riskiness dynamic forecasting

© 2024 Wei Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Słowa kluczowe
Multi-factor quantitative models, Financial markets, Portfolios, Granger causality, Riskiness dynamic forecasting