Wasserstein Distance and Realized Volatility

This research proposes a novel loss function function for neural network models that explores the topological structure of stock realized volatility (RV) data through the addition of Wasserstein Distance (WD). The findings of this research show that the proposed loss statistically significantly improves the forecast accuracy of neural network models for magnitude-dependent error measures, for example Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), but not necessarily for relative error measures, such as Quasi-likelihood (QLIKE). Additionally, this research provides user-friendly open-source code for an easy implementation of the proposed loss function by researchers and practitioners