Gaussian Process Volatility Model

Abstract

The accurate prediction of time-changing variances is an important task in the modeling of financial data. Standard econometric models are often limited as they assume rigid functional relationships for the variances. Moreover, function parameters are usually learned using maximum likelihood, which can lead to overfitting. To address these problems we introduce a novel model for time-changing variances using Gaussian Processes. A Gaussian Process (GP) defines a distribution over functions, which allows us to capture highly flexible functional relationships for the variances. In addition, we develop an online algorithm to perform inference. The algorithm has two main advantages. First, it takes a Bayesian approach, thereby avoiding overfitting. Second, it is much quicker than current offline inference procedures. Finally, our new model was evaluated on financial data and showed significant improvement in predictive performance over current standard models.

Cited by in corpus (9)

• Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders
• Incorporating prior financial domain knowledge into neural networks for implied volatility surface prediction
• Benchmarking Deep Sequential Models on Volatility Predictions for Financial Time Series
• Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes
• Temporal mixture ensemble models for intraday volume forecasting in cryptocurrency exchange markets
• Warped Input Gaussian Processes for Time Series Forecasting
• varycoef: An R Package for Gaussian Process-based Spatially Varying Coefficient Models
• Applications of Gaussian Process Latent Variable Models in Finance
• On MCMC for variationally sparse Gaussian processes: A pseudo-marginal approach