Open AccessStock Price Prediction Using ARIMA, Neural Network and LSTM Models
Author(s) -
Ming-Che Ho,
Hazlina Darman,
Sarah Musa
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1988/1/012041
Subject(s) - autoregressive integrated moving average , mean absolute percentage error , artificial neural network , mean squared error , stock market prediction , stock (firearms) , computer science , econometrics , stock price , moving average , artificial intelligence , machine learning , time series , statistics , stock market , economics , mathematics , engineering , series (stratigraphy) , mechanical engineering , paleontology , horse , biology , computer vision
Since the past decades, prediction of stock price has been an important and challenging task to yield the most significant profit for a company. In the era of big data, predicting the stock price using machine learning has become popular among the financial analysts since the accuracy of the prediction can be improved using these techniques. In this paper, auto-regressive integrated moving average (ARIMA), neural network (NN) and long short-term memory network (LSTM) have been used to predict Bursa Malaysia’s closing prices data from 2/1/2020 to 19/1/2021. All the models will be evaluated using root mean square errors (RMSE) and mean absolute percentage errors (MAPE). The results showed that LSTM able to generate more than 90% of accuracy in predicting stock prices during this pandemic period.