Market Regime Identification Using Hidden Markov Models

Abstract

Market conditions change over time leading to up-beat (bullish) or down-beat (bearish) market sentiments. The concept of bull and bear markets, also known as market regimes, is introduced to describe market status. Since regimes of the total market are not observable and the return can be calculated directly, the modelling paradigm of hidden Markov model is introduced to capture the tendency of financial markets which change their behavior abruptly. In this project we analyze the FTSE 100 and the Euro Stoxx 50 data series via the well-known Hidden Markov Model (HMM). Using this model, we are able to better capture the stylized factors such as fat tails and volatility clustering compared with the Geometric Brownian motion (GBM), and find the market signal to forecast the future market conditions.

Keywords: Hidden Markov model, Parameter estimation