Intraday pairs trading strategies on high frequency data: the case of oil companies

Abstract

This paper introduces novel 'doubly mean-reverting' processes based on conditional modeling to model spreads between pairs of stocks. Intraday trading strategies using high frequency data are proposed based on the model. This model framework and the strategies are designed to capture 'local' market inefficiencies that are elusive for traditional pairs trading strategies with daily data. Results from real data back-testing for two periods show remarkable returns, even accounting for transaction costs, with annualized Sharpe ratios of 3.9 and 7.2 over the periods June 2013-April 2015 and 2008 respectively. By choosing the particular sector of oil companies, we also confirm the observation that the commodity price is the main driver of the share prices of commodity-producing companies at times of spikes in the related commodity market.

Pairs trading with a mean-reverting jump–diffusion model on high-frequency data

“…Ever since this publication, academical interest in statistical arbitrage pairs trading has surged. Key contributions are provided by Vidyamurthy (2004), Elliott et al (2005), Do and Faff (2010), Avellaneda and Lee (2010), Rad et al (2016), and Liu et al (2017). Krauss (2017) identifies five streams of pairs trading research -among them is the timeseries approach which focuses on mean-reverting spreads.…”

“…Krauss (2017) identifies five streams of pairs trading research -among them is the timeseries approach which focuses on mean-reverting spreads. Meaningful representatives are Elliott et al (2005), Bertram (2009Bertram ( , 2010, Avellaneda and Lee (2010), Ekström et al (2011), Cummins and Bucca (2012), Bogomolov (2013), Zeng and Lee (2014), Göncü and Akyıldırım (2016a), and Liu et al (2017). These studies use an Ornstein-Uhlenbeck (OU) process for modeling the price spread between two stocks.…”

“…Bogomolov (2013) extends the method of renko and kagi constructions to pairs trading spread processes, shows their theoretical profitability for the OU process, and examines the strategy performance on the American and Australian stock exchanges from 1996 until 2011. Recently, Liu et al (2017) introduce a doubly mean-reverting process based on conditional modeling to describe spreads. For empirical study, the authors opt for oil stocks of NYSE and NASDAQ from June 2013 to April 2015 and in 2008.…”

“…The vast majority of studies about pairs trading with stochastic differential equations use daily data -a clear drawback within the framework of stochastic processes in continuous time (Bertram 2009, 2010, Avellaneda and Lee 2010, Cummins and Bucca 2012, Bogomolov 2013 Lee 2014, Göncü and Akyıldırım 2016a). Sole exception is provided by Liu et al (2017) who apply frequencies of 5 minutes. We present the first academic study on pairs trading using a minute-by-minute frequency over a sample period of 18 years.…”

Financial Market Predictions with Factorization Machines: Trading the Opening Hour Based on Overnight Social Media Data

“…(2 0 1 8 ) and hedge market exposure day-by-day with corresponding capital expenditures in the S&P 500 index. In accordance with Liu et al (2017) and St u¨b inger and Endres (2 018 ) we set . Following Gatev et al (2006) return computation is based on committed capital, the more common metric in trading literature.…”