The profitability of pairs trading strategy based on linear state-space models and the Kalman filter in Tehran Stock Exchange

Statistical arbitrage as one of the subsets of algorithmic trading refers to strategies that employ some statistical model or method to take advantage of what appears to be mispricing between assets while maintaining a level of market neutrality. One of these strategies is pair trading that implements on two related long-term(co-integration) financial assets. The pair trading strategy of the research is based on the description of the visible process, the remainder of the co-integration model in terms of an invisible mean reverting process. This representation is in a state-space model and solved by the Kalman filter approach and the time of buying and selling is calculated in terms of two probabilities of growth and fall. The profitability of pair trading strategy on 21 stocks from oil product index and basic metal index of Tehran Stock Exchange between 1390-1395 was evaluated according to return and Sharp ratio. The results of the research show that the research method has the daily returns of 0.0048 and Sharp 1.23, which is more profitable in comparison with the pair trading based cointegration and market performance but the average daily its return is in the second place after the co-integration method.