Forecasting Stock Market Realized Variance with Echo State Neural Networks

Abstract

Abstract:Echo State Neural Networks (ESN) were applied to forecast the realized variance time series of 19 major stock market indices. Symmetric ESN and asymmetric AESN models were constructed and compared with the benchmark realized variance models HAR and AHAR that approximate the long memory of the realized variance process with a heterogeneous auto-regression. The results show that asymmetric models generally outperform symmetric ones, indicating that a correlation between volatility and returns plays an important role for volatility forecasting. Additionally, models utilizing a logarithmic transformation of the time series achieved generally better results than models applied directly to the realized variance. Echo State Neural Networks outperformed HAR and AHAR models for several important indices (S&P500, DJIA and Nikkei indices), but on average they achieved slightly worse results than the AHAR model. Nevertheless, the results show that Echo State Neural Networks represent an easy-to-use and accurate tool for realized variance forecasting, whose performance may potentially be further improved with meta-parameter optimization.

Novel hybrid model based on echo state neural network applied to the prediction of stock price return volatility

“…Hence, the search for more accurate forecasting models in specific problems is unavoidable since a general solution may never emerge. Considering the potential of improvement in ESN-based forecasting models for stock volatilities reported by Fičura (2018), and the limitations of the successful HAR models to nonlinear time series forecasting, would a hybrid model that combines the ESN and HAR characteristics deliver more accurate stock price return volatility forecasts?…”

“…It has also emerged in deep specifications such as in Ma, Shen, and Cottrell (2020). Fičura (2018) compares the ESN with HAR models in predicting stock market volatility of several indexes and finds that, on average, the HAR models perform better but also suggests that the ESN has a potential for being improved. Applications of ESN for stock price return forecasting are found in Zhang, Liang, and Chai (2013) and Dan et al (2014).…”