Real‐Time Pricing and Hedging of Options on Currency Futures with Artificial Neural Networks

Abstract

High‐frequency trading and automated algorithm impose high requirements on computational methods. We provide a model‐free option pricing approach with neural networks, which can be applied to real‐time pricing and hedging of FX options. In contrast to well‐known theoretical models, an essential advantage of our approach is the simultaneous pricing across different strike prices and parsimonious use of real‐time input variables. To test its ability for the purpose of high‐frequency trading, we perform an empirical run‐time trading simulation with a tick dataset of EUR/USD options on currency futures of 4 weeks. In very short non‐overlapping 15‐minute out‐of‐sample intervals, theoretical option prices derived from the Black model compete against nonparametric option prices through two different neural network topologies. We show that the approximated pricing function of learning networks is suitable for generating fast run‐time option pricing evaluation as their performance is slightly better in comparison to theoretical prices. The derivation of the network function is also useful for performing hedging strategies. We conclude that the performance of closed‐form pricing models depends highly on the volatility estimator, whereas neural networks can avoid this estimation problem but require market liquidity for training. Nevertheless, we also have to take particular enhancements into account, which give us useful hints for further research and steps. Copyright © 2014 John Wiley & Sons, Ltd.

A Derivatives Trading Recommendation System: the Mid-Curve Calendar Spread Case

“…In parallel to the traditional framework, alternative ways of pricing and trading started to emanate relying on fewer assumptions and more data-driven. We can pinpoint approaches that use NN for option pricing and hedging with daily S&P 500 index daily call options (Gencay & Qi, 2001) as well as for real-time pricing and hedging options on currency futures of EUR/USD at tick level (von Spreckelsen, von Mettenheim, & Breitner, 2014). It is worth to mention other approaches in the derivatives realm, such that the prediction of pricing and hedging errors for equity-linked warrants with Gaussian Process models (Han & Lee, 2008), building machine learning models for predicting option prices over KOSPI 200 Index options (Park, Kim, & Lee, 2014) and a general study on forecasting non-negative option price distributions using Bayesian kernel methods (Park & Lee, 2012).…”

Mid-Curve Recommendation System: a Stacking Approach Through Neural Networks

“…Contrasting with the emphasis that researchers in cash instruments put on return predictability, when we devote our attention to research in derivatives instruments (options, swaps, swaptions, etc.) it is clear that most of the effort is concentrated on pricing these contracts via stochastic calculus [10], [16], [22], [25], with some few exceptions using Neural Networks and other machine learning models for price estimation [14], [23], [27]. When we devote our attention to the asset type that this work is dedicated, interest rate swaptions, a similar pattern persists: most of the research is related to pricing and not to return prediction.…”

A derivatives trading recommendation system: The mid‐curve calendar spread case

“…In parallel to the traditional framework, there is a growing interest in data‐driven alternatives of pricing and trading relying on fewer assumptions. We can pinpoint approaches that use NN for option pricing and hedging with daily S&P 500 index daily call options (Gencay & Qi, ) as well as for real‐time pricing and hedging options on currency futures of EUR/USD at tick level (von Spreckelsen et al, ). It is worth to mention other approaches in the derivatives realm, such that the prediction of pricing and hedging errors for equity‐linked warrants with Gaussian Process models (Han & Lee, ), building machine learning models for predicting option prices over KOSPI 200 Index options (Park et al, ) and a general study on forecasting non‐negative option price distributions using Bayesian kernel methods (Park & Lee, ).…”