An application of Geometric Brownian Motion (GBM) in forecasting stock price of Small and Medium Enterprises (SMEs) / Nur Fizlah Ainaa Khairuddin ... [et al.]

• Main Authors: Khairuddin, Nur Fizlah Ainaa, Ahamad Sofian, Norfarzana, Sukarman, Amalina, Muhamad Yusof, Norliza
• Format: Article
• Language: English
• Published: Universiti Teknologi MARA, Negeri Sembilan 2023
• Subjects: Mathematical statistics. Probabilities
• Online Access: https://ir.uitm.edu.my/id/eprint/83836/1/83836.pdf; https://ir.uitm.edu.my/id/eprint/83836/

The uncertainty and unpredictability of stock prices make investors face difficulty forecasting the future price. There might be a great return or loss in stock investment, which is quite risky for investors. Therefore, to assist investors to make a better decision, this study focuses on how to forecast stock prices of Small and Medium Enterprises (SMEs). Normally, the stock price of SMEs is affordable for all levels of investors since the price is lower (Abidin & Jaffar, 2014). The stock price of SMEs is also more volatile compared to the big and stable companies. Accordingly, there is a need to forecast the future price of the SMEs. There are many methods used to forecast stock prices such as by using fuzzy system (Wang, 2002; Jandaghi et al. 2010) and machine learning (Abolhassani & Yaghoobi, 2010; Patel et al. 2015;). Since stock prices have unpredictable pattern and it follows the random walk, thus Geometric Brownian Motion (GBM) approach is introduced here to forecast stock prices of SMEs. According to Abidin and Jaafar (2014), the two weeks investment duration is the best range to estimate the stock prices. This is because the forecasted prices are found much closer to the actual prices for two weeks duration. This is equivalent to the statement made by Wattanarat et al. (2010) where GBM model is said suitable to forecast in a short period. Therefore, the aim of this study is to forecast stock prices of SMEs for two weeks using the GBM model. In addition, the Mean Absolute Percentage Error (MAPE) is used to calculate the accuracy of the forecasting prices.