Skip to content
All library documents

Using VIX Futures Curve Shape to Choose Trading Positions

Article arXiv papers · Author: M. Avellaneda et al.
Read the original

Summary

This paper proposes a day-ahead strategy for taking long or short positions in VIX futures. It treats the futures term structure as a Markov process and selects a position to maximize expected utility based on the curve’s current shape and level.

The authors represent the relationship among the curve, futures positions, and expected utility with a deep neural network. They report that out-of-sample backtests show reasonable portfolio performance and that the strategy switches between long and short exposure as market conditions change. The supplied description does not give numerical performance measures, transaction costs, risk controls, or details of the backtest design. Its results therefore indicate a proposed modeling approach and reported historical evidence, but do not establish how the strategy would perform live or across other periods.

Key ideas

  • The strategy selects VIX futures positions for a one-day-ahead horizon.
  • Position choice depends on the current level and shape of the VIX futures curve.
  • The term structure is modeled as a Markov process.
  • A deep neural network maps the curve and positions to expected utility.
  • Out-of-sample backtests are described as showing reasonable performance, but the summary omits costs and detailed risk results.

Tags

FuturesVolatilityMachine learningBacktesting
Full text
# Trading Signals In VIX Futures


# Trading Signals In VIX Futures









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.