Modelling and Forecasting Stock Market Trend Using Markov Chain Process: A Study of Dar Es Salam Stock Exchange, Tanzania

This study applies a Markov Chain model to forecast the behaviour of the Dar Es Salaam Stock Exchange (DSE) market. DSE serves as the only official platform for share trading in Tanzania. The application of the Markov Chain model in forecasting future states relies on the inherent randomness exhibited by the DSE market. This study utilizes the Markov Chain model to forecast future conditions based on the inherent randomness observed in the DSE market. It aims to explore the long-term dynamics of the market, estimate how often specific states are revisited, and calculate the expected time for the market to return to those states. The analysis utilizes secondary data from 1,847 trading days of DSE index values, covering the period from August 25, 2014, to November 18, 2021, sourced from the DSE office. The study reveals that in the long run, regardless of the current state of the DSE market, share prices are most likely to remain stable, with a probability of approximately 91%, while the chances of depreciation and appreciation are relatively low, at around 5% and 4%, respectively. This indicates a relatively steady market environment with minimal and predictable price movements, reflecting low long-term volatility. Such stability may appeal to long-term, risk-averse investors, but it also highlights limited opportunities for short-term speculative gains. The findings underscore the need to enhance market activity and liquidity by encouraging more company listings, increasing public awareness, and improving market infrastructure. These efforts could help develop a more vibrant and responsive stock market, thereby strengthening the DSE’s role in supporting broader economic development.