Forecasting VIX using Bayesian Deep Learning
This work addresses volatility forecasting for financial markets, presenting incremental improvements in model performance and uncertainty estimation.
The paper tackled forecasting the VIX volatility index using Bayesian deep learning, showing that a Temporal Convolutional Network (TCN) with specific priors achieved an RMSE of around 0.189 and improved uncertainty calibration.
Recently, deep learning techniques are gradually replacing traditional statistical and machine learning models as the first choice for price forecasting tasks. In this paper, we leverage probabilistic deep learning for inferring the volatility index VIX. We employ the probabilistic counterpart of WaveNet, Temporal Convolutional Network (TCN), and Transformers. We show that TCN outperforms all models with an RMSE around 0.189. In addition, it has been well known that modern neural networks provide inaccurate uncertainty estimates. For solving this problem, we use the standard deviation scaling to calibrate the networks. Furthermore, we found out that MNF with Gaussian prior outperforms Reparameterization Trick and Flipout models in terms of precision and uncertainty predictions. Finally, we claim that MNF with Cauchy and LogUniform prior distributions yield well calibrated TCN and WaveNet networks being the former that best infer the VIX values.