Stock Price Prediction using Support Vector Machine in the Second Wave of Covid-19 Pandemic
Abstract
The aim of the research is to predict The Jakarta Composite Index (JKSE) when the second wave of the Covid-19 occurred in Indonesia. The method used in this research is Support Vector Machine (SVM). The data used in this study is JKSE for period April 2021 to August 2021. The data is divided into two parts, the training data and the testing data. The training data starts from April 1st to July 30th 2021. The data used as ground truth is the data from August 2nd to August 31st 2021. To get the best hyperparameter, the research uses Grid Search with RBF kernel. The results show the best hyperparameters using RBF kernel are C=100, =0.01, and = 3. The prediction result obtained tends to be stable and has a slight decrease. This result if we compared with the cumulative cases and the total recovery cases of the Covid-19, the investor has a positive sentiment towards the Indonesian government in solving the Covid-19 pandemic.
Moraref