Trading Signals In VIX Futures

TL;DR

This paper introduces a novel deep learning-based trading strategy for VIX futures that models the term structure as a Markov process and optimizes expected utility for daily trading decisions.

Contribution

It presents a new approach combining Markov models and neural networks to improve VIX futures trading strategies.

Findings

Out-of-sample backtests show reasonable portfolio performance.

Strategy adapts positions based on market environment.

Neural network effectively models the VIX futures curve.

Abstract

We propose a new approach for trading VIX futures. We assume that the term structure of VIX futures follows a Markov model. Our trading strategy selects a position in VIX futures by maximizing the expected utility for a day-ahead horizon given the current shape and level of the term structure. Computationally, we model the functional dependence between the VIX futures curve, the VIX futures positions, and the expected utility as a deep neural network with five hidden layers. Out-of-sample backtests of the VIX futures trading strategy suggest that this approach gives rise to reasonable portfolio performance, and to positions in which the investor will be either long or short VIX futures contracts depending on the market environment.