Simulating Stock Prices Using Geometric Brownian Motion in the Malaysian Stock Market.

Abstract

Among these mathematical models, the Geometric Brownian Motion (GBM) model plays a pivotal role in predicting stock prices. Bursa Malaysia, the financial sector's foundation, offers a vibrant venue for securities trading, which is essential to the growth of the country's economy. This study aims to evaluate the GBM model’s performance in various market contexts in Malaysia, particularly considering different market capitalizations and industry sectors over various time frames. The sample for this study includes companies from the sectors of Financial Services, Property, Industrial Products & Services, and Transportation & Logistics and Daily stock price data obtained from Yahoo Finance from 2019 to 2023 used in the study. The methodology involves applying GBM to simulate short-term and long-term stock prices and evaluating the accuracy using statistical measures MAPE and RMSE. The findings reveal that the GBM model exhibits high accuracy in short-time forecasting across a diverse range of stocks, however, its efficiency diminishes over more extended forecasting periods also large-cap stocks yield more stocks and more accurate short-term predictions, also the model’s effectiveness varies significantly across the sector. This study establishes the model's effectiveness in short-term forecasting but cautions against its reduced accuracy for long-term predictions under varying market conditions. The research emphasizes the importance of a multifaceted approach to financial modelling, highlighting the need for careful application in long-term investment strategies and policy development within markets like Bursa Malaysia.