CNN-based Realized Covariance Matrix Forecasting
This addresses the challenge of high-dimensional covariance forecasting in finance, offering a method that avoids structural assumptions, though it is incremental as it builds on existing deep learning techniques.
The authors tackled the problem of forecasting realized covariance matrices for asset returns, which is crucial in finance but often suffers from strong assumptions and dimensionality issues, and they proposed a CNN and ConvLSTM-based model that demonstrated excellent forecasting ability compared to advanced volatility models.
It is well known that modeling and forecasting realized covariance matrices of asset returns play a crucial role in the field of finance. The availability of high frequency intraday data enables the modeling of the realized covariance matrices directly. However, most of the models available in the literature depend on strong structural assumptions and they often suffer from the curse of dimensionality. We propose an end-to-end trainable model built on the CNN and Convolutional LSTM (ConvLSTM) which does not require to make any distributional or structural assumption but could handle high-dimensional realized covariance matrices consistently. The proposed model focuses on local structures and spatiotemporal correlations. It learns a nonlinear mapping that connect the historical realized covariance matrices to the future one. Our empirical studies on synthetic and real-world datasets demonstrate its excellent forecasting ability compared with several advanced volatility models.