Fuzzy Time Series and Geometric Brownian Motion in Forecasting Stock Prices in Bursa Malaysia

Authors

  • Nor Hayati Shafii Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA Cawangan Perlis, Arau Campus
  • Nur Ezzati Dayana Mohd Ramli Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA Cawangan Perlis, Arau Campus
  • Rohana Alias Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA Cawangan Perlis, Arau Campus
  • Nur Fatihah Fauzi Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA Cawangan Perlis, Arau Campus

DOI:

https://doi.org/10.24191/ji.v14i2.241

Keywords:

Forecasted values, stock market, Fuzzy Time Series, Geometric Brownian Motion

Abstract

Every country has its own stock market exchange, which is a platform to raise capital and is a place where shares of listed company are traded. Bursa Malaysia is a stock exchange of Malaysia and it is previously known as Kuala Lumpur Stock Exchange. All over the world, including Malaysia, it is common for investors or traders to face some loss due to wrong investment decisions. According to the conventional financial theory, there are so many reasons that can lead to bad investment decisions. One of them is confirmation bias where an investor has a preconceived notion about an investment without a good information and knowledge. In this paper, we study the best way to provide good information for investors in helping them make the right decisions and not to fall prey to this behavioral miscue. Two models for forecasting stock prices data are employed, namely, Fuzzy Time Series (FTS) and Geometric Brownian Motion (GBM). This study used a secondary data consisting of AirAsia Berhad daily stock prices for a duration of 20 weeks from January 2015 to May 2015. The 16-weeks data from January to April 2015 was used to forecast the stock prices for the 4-weeks of May 2015. The results showed that FTS has the lowest values of the Mean Absolute Percentage Error (MAPE) and the Mean Square Error (MSE), which are 1.11% and MYR20.0011, respectively. For comparison, for GBM, the MAPE is 1.53% and the MSE is MYR2 0.0017. The findings imply that the FTS model provides a more accurate forecast of stock prices. Keywords: Forecasted values, stock market, Fuzzy Time Series, Geometric Brownian Motion

References

Abdelmoula, D. (2006). Stock price modelling : Theory and Practice. Thesis. Vrije Universiteit. Amsterdam.
Abidin, S. N. Z., & Jaffar, M. M. (2014). Forecasting share prices of small size companies in Bursa
Malaysia using geometric Brownian motion. Applied Mathematics and Information Sciences, 8(1),
107–112. https://doi.org/10.12785/amis/080112
Dani, S., & Sharma, S. (2013). Forecasting rainfall of a region by using fuzzy time series. Asian Journal
of Mathematics and Applications, 2013(1), 1–10.
Hakan, C., Egrioglu, E., Yolcu, U., & Uslu, V. R. (2014). A high order seasonal fuzzy time series model and application to international tourism demand of Turkey, Journal of Intelligent & Fuzzy Systems, 26, 295–302. https://doi.org/10.3233/IFS-120738
Huang, Y. (2015). Weighted Fuzzy Time Series Model for Load Forecasting. NCITPA, 81–90.
Stevenson, M., & Porter, J. E. (2009). Fuzzy Time Series Forecasting Using Percentage Change as the Universe of Discourse. World Academey of Science, Engineering and Technology, 55, 154–157.
W, F. A., Affianti, I. R., & Putri, E. R. M. (2018). Stock price prediction using geometric Brownian motion. Journal of Physics: Conference Series, 974(1).
Wilmott, P. (2007). Introduces Quantitative Finance. (2nd Ed.). West Sussex: John Wiley & Sons Ltd.

Downloads

Published

2019-11-27