Hidden Markov Model for Stock Selection

Nguyet Nguyen,Dung Nguyen

doi:10.3390/risks3040455

Abstract

The hidden Markov model (HMM) is typically used to predict the hidden regimes of observation data. Therefore, this model finds applications in many different areas, such as speech recognition systems, computational molecular biology and financial market predictions. In this paper, we use HMM for stock selection. We first use HMM to make monthly regime predictions for the four macroeconomic variables: inflation (consumer price index (CPI)), industrial production index (INDPRO), stock market index (S&P 500) and market volatility (VIX). At the end of each month, we calibrate HMM’s parameters for each of these economic variables and predict its regimes for the next month. We then look back into historical data to find the time periods for which the four variables had similar regimes with the forecasted regimes. Within those similar periods, we analyze all of the S&P 500 stocks to identify which stock characteristics have been well rewarded during the time periods and assign scores and corresponding weights for each of the stock characteristics. A composite score of each stock is calculated based on the scores and weights of its features. Based on this algorithm, we choose the 50 top ranking stocks to buy. We compare the performances of the portfolio with the benchmark index, S&P 500. With an initial investment of $100 in December 1999, over 15 years, in December 2014, our portfolio had an average gain per annum of 14.9% versus 2.3% for the S&P 500.

Highlights

IntroductionThe states of a system can be modeled as a Markov chain in which each state depends on the previous state in a non-deterministic way
In many financial problems, the states of a system can be modeled as a Markov chain in which each state depends on the previous state in a non-deterministic way
After analyzing the performances of the benchmark market index (S&P 500) on two defined regimes of different economic indicators, we found that the S&P 500 performs significantly different across different states of four macroeconomic variables: inflation (consumer price index (CPI)), industrial production index (INDPRO), stock market index (S&P 500) and market volatility (VIX), a measure of market expectations of near-term volatility conveyed by S&P 500 stock index option prices

Summary

Introduction

The states of a system can be modeled as a Markov chain in which each state depends on the previous state in a non-deterministic way. Timmermann [4] used HMM with four states and multiple observations to study asset allocation decisions based on regime switching in asset returns. Nguyen [6] used HMM with both single and multiple observations to forecast economic regimes and stock prices. The momenta of a stock depends on many different factors, such as the corporate financial condition and management and the overall economy and industry conditions These factors and corresponding stock returns vary widely over different macro regimes. In this paper, we develop a new approach of HMM: making monthly stock selections based on their historical performances on economic regimes. We analyze the performances of stocks’ returns on each macro regime to make stock selections instead of applying HMM directly to predict their prices.

A Brief Introduction of the Hidden Markov Model

Forward Algorithm

The Viterbi Algorithm

Baum–Welch Algorithm

Describe the Model and Data

Data Selections

Description of Model

Regimes of Macro Variables

Stock Selection

Conclusions