Comparison of Support Vector Machine (SVM) and Linear Regression (LR) for Stock Price Prediction

Stocks are a type of investment with high risk and high returns because the data is dynamic. One of the capital market participating companies is PT. Vale Indonesia or commonly known by its issuer code INCO. Production PT. Vale Indonesia supplies 4% of the world’s nickel needs. In the future, the need for nickel will continue to increase because it is used for electric vehicle batteries. As demand increases, selling prices will increase and share price movements will fluctuate. Therefore, we need a prediction that is able to describe stock prices based on stock price movements in the previous period. This research compares the Support Vector Machine (SVM) and Linear Regression (LR) algorithms in predicting stock prices. This research is expected to obtain an algorithm with the best level of accuracy as a consideration for investors in choosing an algorithm to make predictions. The results this research state that Linear Regression (LR) algorithm is better than the Support Vector Machine (SVM) in predicting stock prices at PT. Vale Indonesia. The best Linear Regression Model divides the data into 90% training data and 10% test data to obtain an RMSE of 42.82, which means it is quite good at making predictions because it is quite close to zero. Meanwhile, the best Support Vector Machine model divides the data into 90% training data and 10% testing data to obtain an RMSE of 64.32, which means the model is not good at making predictions because the accuracy results are not close to zero.