DETECTION OF JKSE STOCK PRICE CHANGES DURING THE COVID-19 PANDEMIC USING THE GAUSSIAN PROCESS METHOD Naqisya Arifani, Sapto Wahyu Indratno, Dian Anggraini, Enrico Antonius, Kahfi Rizky Kosasih
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Jl. Ganesa No. 10, Lb. Siliwangi, Bandung, 40132, Indonesia
Abstract
The COVID-19 Pandemic has had a significant impact on the Indonesian stock market, particularly on the Jakarta Composite Index (JKSE). This study aims to detect change points in the JKSE stock prices during the COVID-19 pandemic in Indonesia using the Gaussian Process method. The motivation of the research is to understand and analyze stock market fluctuations during crisis situations like the pandemic, which can affect investment decisions. The JKSE was chosen as it reflects the condition of the Indonesian stock market. This study utilizes weekly JKSE stock price data from 2019 to 2023, analyzed using the Gaussian Process method with Radial Basis Function (RBF) and Matern kernels. The analysis involves calculating the Generalized Likelihood Ratio Test (GLRT) values to detect change points with varying threshold of 10, 20, 30, 40, and 45 to assess detection sensitivity. The results indicate the several significant events during the COVID-19 pandemic in Indonesia caused sharp increases in the GLRT values. Low and stable GLRT values indicate normal market conditions without significant changes or high volatility. In conclusion, the Gaussian Process method with RBF and Matern kernels is effective in detecting significant changes in JKSE stock prices during the COVID-19 pandemic. This methods aids investors in monitoring market volatility and planning adaptive investment strategies to navigate stock market fluctuations in crisis situations such as the pandemic.
Keywords: Gaussian Process, Change Point Detection, Pandemic, COVID-19, Market Volatility
