Hybrid deep learning combined with traditional financial models: Application of RNN models and GARCH-Family Model for Natural Gas Price Volatility Forecasting

Abstract

The natural gas market has significant commonalities with the general financial market, especially its time series data are often non-stationary and show different fluctuation characteristics due to different market conditions. Therefore, accurate forecasting of natural gas price volatility requires a correct handling of the unique characteristics of its time series. In this paper, GARCH model and TGARCH model are specially selected to capture the volatility heteroscedasticity generated in different market scenarios, and IGARCH model is used to ensure that the model can still maintain high prediction accuracy when the time series is non-stationary. In order to deal with the long-term dependence of natural gas prices on time series, this paper introduces the LSTM model and the GRU model, both of which are variants of recurrent neural network (RNN). Thus we obtain the GARCH-IGARCH-TGARCH-LSTM/GRU model. It is worth noting that this model is applied to the field of natural gas price volatility prediction for the first time, which provides a new research perspective for in-depth understanding and accurate prediction of natural gas market volatility. We use the natural gas futures price index from June 2013 to June 2023 for the simulation test. Using 100 repeated experiments, we verify the robustness of the GARCH-IGARCH-TGARCH-GRU model in volatility forecasting and demonstrate its superior forecasting accuracy with a mean square error (MSE) of 0.22 and a mean absolute error (MAE) of 0.13. In the face of market breaks and extreme events, the integrated model shows higher adaptability and robustness. This study not only provides a powerful volatility forecasting tool for natural gas market participants, but also provides a strong demonstration of the universality of this type of model.