A Novel Algorithmic Trading Strategy using Hidden Markov Model for Kalman Filtering Innovations

The development of algorithmic trading has been one of the most prominent trends in finance and its applications. Hidden Markov Models (HMMs) help enhance the predictive power of statistical models and improve trading strategies for data scientists and algorithmic traders. In recent years there has been growing interest in investigating the pairs trading and multiple trading based on robust Kalman filtering (KF) using data-driven innovation volatility forecasts (DDIVF). KF algorithms were successfully applied in pairs trading with two cointegrated assets using DDIVF as a method for forecasting non-normal innovation volatility. In this paper a novel combined pairwise trading strategy is proposed by combining HMM and DDIVF to further optimize trading signals in different market regimes. The results of the numerical experiments on two cointegrated stocks show that the proposed profitable trading strategy using DDIVF-HMM outperforms the recently studied robust trading strategy using DDIVF alone.

Automated summary

The development of algorithmic trading, particularly using Hidden Markov Models (HMMs) and robust Kalman filtering (KF) with data-driven innovation volatility forecasts (DDIVF), has shown promising results in enhancing predictive power and improving trading strategies. A novel combined pairwise trading strategy utilizing HMM and DDIVF has demonstrated superior performance compared to using DDIVF alone in numerical experiments with two cointegrated stocks.