<![CDATA[JKSE is an index that can describe the condition and stability of the Indonesian economy. JKSE has a very fast movement and has large fluctuations because the JKSE is a joint stock so predicting its movement can be a little difficult. Due to the difficulties in forecasting the JKSE stock price, the right algorithm is needed to have accurate forecasting results. The results of the three algorithms will be compared using T-Test to evaluate the performance of the three algorithms in predicting the movement of the JKSE stock. The results of the comparison between linear regression algorithms, neural networks, and support vector machines, it is found that the neural network algorithm has the best performance with an RMSE value of 14,660. Then the backward elimination method was used in the model, it was found that the performance of the algorithm in that model had an increase, except for the linear regression algorithm. The neural network algorithm plus the backward elimination method is the best algorithm with an RMSE value of 10,895.]]>
Copyrights © 2022
