One of the online trades is stock trading on the stock exchange. To increase the number of investors, the government invites the public to invest in the capital market by buying shares regularly and periodically in the form of shares. With the increase in potential investors in the stock market, deep knowledge about stock trading is needed so that the returns are as desired. This research can help to make it easier for the public to predict the desired stock price through machine learning technology even though they do not have more in-depth technical knowledge about stocks. Three types of algorithms RNN, LSTM, GRU are used to find the best method by optimizing parameters so as to get an r-square error of 0.96 through the number of epochs of 100 and a learning rate of 0.01.