Abstract
A mathematical model represents real-world systems, processes, or phenomena that use logical relations, equations, variables, and mathematical concepts. It plays a pivotal role in understanding, analysing, and predicting system behaviour through equations, charts, graphs, and computer simulations. Geometric Brownian motion (GBM) has emerged as a highly effective mathematical model for stock price prediction. It incorporates random terms representing the stochastic nature of price movements over time. The success of the GBM model hinges on its accurate parameter estimation. To predict stock prices efficiently with GBM, one must ascertain returns, utilising these returns to calculate drift and volatility. This chapter utilises a modified mean growth rate (MGR) derived from actual data on Malayan Banking Berhad’s (Maybank) stock prices from 2011 to 2022. This modification aims to tailor stochastic elements in the GBM equation. The resulting modified MGR effectively captures Maybank’s stock price trend, displaying minimal deviation from actual data. It is used to project stock prices up to 2050. Numerical methods, including the Adams-Bashforth predictor-corrector, three-step predictor-corrector, and Runge-Kutta 4th-order methods, are deployed to make future price predictions, while absolute and relative errors are used to assess the prediction accuracy. These findings will empower investors with crucial information for making well-informed decisions and achieving profitable outcomes.