UMN Knowledge Center

LSTM-RNN Automotive Stock Price Prediction

Johan, Kevin and Young, Julio Cristian and Hansun, Seng (2019) LSTM-RNN Automotive Stock Price Prediction. International Journal of Scientific & Technology Research, 8 (9). ISSN 2277 – 8616

Full text not available from this repository.
Official URL: https://www.ijstr.org/final-print/sep2019/Lstm-rnn...

Abstract

Stock is a securities or paper sheet as proof of ownership of a company. In terms of buying and selling a stock, stock price information is very important for the investors, since the purchase of stock usually will be made when the stock at the lowest price and the sale of stock will be made at the highest price. The focus of this study is to use the Long Short Term Memory algorithm to predict stocks’ price in automotive companies. The Long Short Term Memory algorithm is often used for prediction application, for example, in the analysis and implementation of Long Short Term Memory Neural Network in bitcoin prices prediction. This research was conducted using five automotive stock data that were taken from Yahoo Finance! The research experiments were conducted to get the effect of the number of hidden layer and epochs on the accuracy of stock predictions. From the results of the experiments, we found that the more usage of hidden layers and epochs will make the accuracy results better.

Item Type: Article
Subjects: 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 005 Computer Programming (Algorithm, Programming Language, Applications, Software, Data Security)
300 Social Sciences > 330 Economics > 332 Financial Economics (Shares, Investment)
600 Technology (Applied Sciences) > 620 Engineering > 629 Other Branches of Engineering (Aerospace, Aviation, Astronautics, Robotics)
700 Arts and Recreation
Divisions: Fakultas Teknik Informatika > Program Studi Informatika
Depositing User: mr admin umn
Date Deposited: 12 Oct 2021 07:48
Last Modified: 12 Oct 2021 07:48
URI: http://kc.umn.ac.id/id/eprint/18700

Actions (login required)

View Item View Item