Predicting Stock Price Using Convolutional Neural Network and Long Short Term Memory (Case Study: Stock of BBCA)

Stocks are capital market instruments capable of creating profits for investors. However, stocks have a fluctuating nature that can lead to risk, so price predictions are needed to reduce this risk. Stock price prediction can use various methods such as deep learning. This study aims to predict stock price using Convolution Neural Network (CNN) and Long Short Term Memory (LSTM), with the application carried out at the stock price of Bank Central Asia (BBCA) for the period between July 1, 2005 and December 30, 2022. Data division uses a ratio of 70% for training and 30% for testing. To maximize prediction results, we select the best hyperparameter combinations using Grid Search. The prediction results show that CNN is better to LSTM, where CNN produces RMSE values of 488.992, R2 83.8%, and MAPE 6.5%.