Market-Neutral Trading with Fuzzy Inference, a New Method for the Pairs Trading Strategy

Mehmet Bayram; Muzaffer Akat

doi:10.5755/j01.ee.30.4.14350

Authors

Mehmet Bayram Marmara University, Turkey
Muzaffer Akat Ozyegin University, Turkey

DOI:

https://doi.org/10.5755/j01.ee.30.4.14350

Keywords:

market-neutral trading, statistical arbitrage, pairs trading, fuzzy inference, decision making

Abstract

Financial pricing and prediction of stock markets is a specific and relatively narrow field, which have been mainly explored by mathematicians, economists and financial engineers. Prediction with the purpose of making profits in a martingale domain is a hard task. Pairs trading, a market neutral arbitrage strategy, attempts to resolve the drawback of unpredictability and yield market independent returns using relative pricing idea. If two securities have similar characteristics, so should their prices. Deviation from the acceptable similarity range in prices is considered an anomaly, and whenever noticed, trading is executed assuming the anomaly will correct itself.

This work proposes a fuzzy inference model for the market-neutral pairs trading strategy. Fuzzy logic lets mimicking human decision-making in a complex trading environment and taking advantage of arbitrage opportunities that the crisp models may miss to acquire for the trade decision-making. Spread between two co-integrated stocks and volatility of the spread is used as decision-making inputs. Spread is a measure of the distance between two stocks and volatility is an indicator of how soon the spread would disappear. We conclude that fuzzy engine contributes to the profitability and efficiency of pairs trading type of strategies.

Author Biographies

Mehmet Bayram, Marmara University, Turkey

Mehmet Bayram is a PhD candidate at the Institute for Graduate Studies in Pure and Applied Sciences in Marmara University Department of Industrial Engineering. He received a bachelor's degree in Industrial Engineering from the Air Force Academy and a master's degree in the same field from Eskisehir Osmangazi University. His recent research is mainly based on probability theory and statististical arbitrage techniques of the volatile markets.

Muzaffer Akat, Ozyegin University, Turkey

Asst.Prof.Dr. Akat obtained his BS in Mathematics from Boğaziçi University, his MS and PhD in Mathematics from Stanford University. Before completing his masters degree, Dr. Akat worked as an analyst in Global Securities and as a consultant at McKinsey & Co.'s Istanbul Office as an associate. During his PhD studies, he worked at Morgan Stanley, New York, as an associate in the Fixed Income Division. He also taught in the Computational Finance program at Carnegie Mellon University. He specializes in the applications of partial differential equations and probability theory to mathematical finance. His research mainly focuses on stochastic volatility models in derivatives pricing and credit risk. Dr. Akat teaches courses on financial engineering, derivatives, statistics, and portfolio management.