Comparison of stock price model with GBM and ABM for the share price of PT. Ciputra Development Tbk

Abstract

The aim of this research is to compare the stock price model of PT. Ciputra Development Tbk. i.e. between the ABM (Arithmetic Brownian Motion) model and the GBM (Geometric Brownian Motion) model. The measures of the goodness of the model are used MAPE (Mean Absolute Percentage Error), RMSE (Root Mean Square Error) and MAE (Mean Absolute Error). The data used is stock prices from August 11, 2020 to March 26, 2021 and is used to predict stock prices for the next 59 days, namely from March 29, 2021 to June 28, 2021. Simulation studies with repetitions of B=1000 times are used to calculate MAPE, RMSE and MAE and used to test whether the results are significantly different or not (with a level of significance α = 5%). The results obtained if the ABM model is used are MAPE = 19.60 %, RMSE = 238.84 and MAE = 200.96, while when GBM is used, they are MAPE = 24.23 %, RMSE = 293.86 and MAE = 249.27. The significant difference test (t.test) of the two results showed that the two results were significantly different. As a result, in this case the ABM model is more suitable to be used for the stock price data. This research can be developed for comparison of other stock price models such as the GBM model with jump.