Trend Analysis of BSE Stock Prices Using Hidden Markov Models and Viterbi Algorithm

Abstract

Many forecasting techniques have been put forth and used in recent years to predict stock market trends. Recently, many researchers developed models based on Artificial Neural Network (ANN), Support Vector Machine (SVM), Fuzzy Logic (FL) and Moving Average (MA). This paper presents the trend analysis of the stock market prediction using the Hidden Markov Model and Viterbi algorithm with a 1-day, 2-day, 3-day, 4-day and 5-day variation in the close value for the specified time frame. In this work, we developed a BSE price forecasting model based on Hidden Markov Model due to its proven fittingness for modeling vigorous systems and pattern classification. We apply the HMM methodology to forecast the BSE closing price from Jan 2021 to Dec 2021 using available past datasets from Investopedia. The trend percentage of stock prices, which is computed for every observed sequence and hidden sequence, is provided by the probability values π. In situations of uncertainty, decision makers can use the proportion of probability values derived from the steady state probability distribution as a guide when making judgments.