Neural networks and arbitrage in the VIX
- PDF / 1,570,375 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 30 Downloads / 213 Views
Neural networks and arbitrage in the VIX A deep learning approach for the VIX Joerg Osterrieder1 · Daniel Kucharczyk2 · Silas Rudolf3 · Daniel Wittwer4 Received: 29 December 2018 / Accepted: 20 July 2020 / Published online: 13 August 2020 © The Author(s) 2020
Abstract The Chicago Board Options Exchange Volatility Index (VIX) is considered by many market participants as a common measure of market risk and investors’ sentiment, representing the market’s expectation of the 30-day-ahead looking implied volatility obtained from real-time prices of options on the S&P 500 index. While smaller deviations between implied and realized volatility are a well-known stylized fact of financial markets, large, time-varying differences are also frequently observed throughout the day. Furthermore, substantial deviations between the VIX and its futures might lead to arbitrage opportunities on the VIX market. Arbitrage is hard to exploit as the potential strategy to exploit it requires buying several hundred, mostly illiquid, out-of-the-money (put and call) options on the S&P 500 index. This paper discusses a novel approach to predicting the VIX on an intraday scale by using just a subset of the most liquid options. To the best of the authors’ knowledge, this the first paper, that describes a new methodology on how to predict the VIX (to potentially exploit arbitrage opportunities using VIX futures) using most recently developed machine learning models to intraday data of S&P 500 options and the VIX. The presented results are supposed to shed more light on the underlying dynamics in the options markets, help other investors to better understand the market and support regulators to investigate market inefficiencies. Keywords VIX · SPX · Neural network · LSTM · Deep learning · Arbitrage · Market manipulation · Random forests JEL Classification A00 · C00 · G00
* Joerg Osterrieder [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
98
Digital Finance (2020) 2:97–115
1 Introduction The VIX index has been subject to claims of manipulation over the last few years, see, e.g., Griffin and Shams (2017). We will analyze intra-day data for S&P 500 options to predict the VIX, and, using neural networks, to show how one can exploit potential arbitrage opportunities without having to buy and sell several hundred out-of-the-money put and call options, as described by the VIX methodology (Exchange 2009). On February 5, 2018, the VIX moved the most in a single day in the index’s 25-year history. The VIX and the VIX futures deviated substantially from each other on that day, which was one of the motivations behind our analysis. Another anecdotal evidence, showing the impact of SPX option trades on the VIX, is April 18, 2018. Shortly after the monthly settlement auction that determines the price for VIX options and futures, the VIX spiked as much as eleven percent within 1 h. A trade of 13,923 May puts on the S&P 500 with a strike price of 1200, worth roughly $2.1 million, took pl
Data Loading...
