Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Data

TL;DR

This paper compares various deep learning models for volatility prediction across multiple assets, demonstrating that advanced architectures like the Temporal Fusion Transformer generally outperform classical models and shallow networks.

Contribution

It provides a comprehensive comparison of deep learning architectures for volatility forecasting, highlighting the superior performance of the Temporal Fusion Transformer over traditional methods.

Findings

Temporal Fusion Transformer outperforms classical GARCH models

Deep architectures outperform shallow networks in volatility prediction

Results are statistically significant across multiple assets

Abstract

This study aims to compare multiple deep learning-based forecasters for the task of predicting volatility using multivariate data. The paper evaluates a range of models, starting from simpler and shallower ones and progressing to deeper and more complex architectures. Additionally, the performance of these models is compared against naive predictions and variations of classical GARCH models. The prediction of volatility for five assets, namely S&P500, NASDAQ100, gold, silver, and oil, is specifically addressed using GARCH models, Multi-Layer Perceptrons, Recurrent Neural Networks, Temporal Convolutional Networks, and the Temporal Fusion Transformer. In the majority of cases, the Temporal Fusion Transformer, followed by variants of the Temporal Convolutional Network, outperformed classical approaches and shallow networks. These experiments were repeated, and the differences observed between the competing models were found to be statistically significant, thus providing strong encouragement for their practical application.