A Novel Machine Learning-assisted Pairs Trading Approach for Trading Risk Reduction

The cryptocurrency market has been growing rapidly in recent years. The volume of transactions and the number of participants in the cryptocurrency market makes it huge enough that we cannot ignore it. At the same time, the global stock market has also reached a new height in the past two years. However, due to the COVID epidemic and other political and economic-related factors in the last two years, the uncertainty in the capital market remains high, and short-term large fluctuations occur frequently;thus, many investors have suffered substantial losses. Pairs trading, an advanced statistical arbitrage method, is believed to hedge the risk and profit off the market regardless of market condition. Amongst the vast literature on pairs trading, there have been investors trading a pair of cryptocurrencies or a pair of stocks using machine learning or empirical methods. This research probes the boundary of utilizing machine learning methods to do pairs trading with one stock asset and another cryptocurrency. Briefly, we built an assets pool with both stocks and cryptocurrencies to find the best trading pair. In addition, we applied mainstream machine learning models to the trading strategy. We finally evaluated the accuracy of the proposed method in prediction and compared their returns based on the actual U.S. Stock and Cryptocurrency Market data. The test results show that our method outperforms other state-of-the-art methods. © 2022 IEEE.

Intra-day co-movements of crude oil futures: China and the international benchmarks.

Investigating the co-movements between crude oil futures helps to understand the integration of the global markets. This paper focuses on Shanghai crude oil futures (INE) and study its co-movements with the international benchmarks of WTI and Brent crude oil futures in intra-day day and night trading sessions. A complex network model framework is proposed to analyse the intra-day co-movement patterns labelled by a functional data clustering approach on intra-day return curves. Our findings indicate INE is more integrated with the global market during the night session, but it shows a regional fractional effect during the day session. Based on the revealed dynamics of co-movement patterns, we further design a pairs trading strategy between INE crude oil futures and the international benchmarks. The simulation results show that the pairs trading strategy can be promisingly profitable, even during market turmoil phases.

Are Pair Trading Strategies Profitable during COVID-19 Period?

Pair trading strategy is a well-known profitable strategy in stock, forex, and commodity markets. As most of the world stock markets declined during COVID-19 period, therefore this study is going to observe whether this strategy is still profitable after COVID-19 pandemic. One of the powerful algorithms of DBSCAN under the umbrella of unsupervised machine learning is applied and three clusters were formed by using market and accounting data. The formation of these three clusters was based on book value per share, earning per share, classification of sector, market capitalisation and with other factors formed from PCA on the returns of daily data of six months of the 80 sample firms for year 2019-2020. An average of -0.32% average excess monthly return with Sharpe ratio of -0.0012 and Treynor ratio of -0.0231 is to be observed in COVID-19 pandemic period. However, the result of risk-adjusted performance under Jensen's alpha is observed to be insignificant. The policy implication of this study, for different portfolios and fund managers is suggested to use machine learning approach to get positive and higher returns for their clients. © 2022 World Scientific Publishing Company.