RSIS International

Submission Deadline: 17th December 2024
Last Issue of 2024 : Publication Fee: 30$ USD Submit Now
Submission Deadline: 20th December 2024
Special Issue on Education & Public Health: Publication Fee: 30$ USD Submit Now
Submission Deadline: 05th January 2025
Special Issue on Economics, Management, Psychology, Sociology & Communication: Publication Fee: 30$ USD Submit Now

International Journal of Research and Scientific Innovation (IJRSI) | Volume V, Issue VII, July 2018 | ISSN 2321–2705

Stock Market Index Prediction Using Multilayer Perceptron and Long Short Term Memory Networks: A Case Study on BSE Sensex

R. Arjun Raj#

IJRISS Call for paper

#Research Scholar, APJ Abdul Kalam Technological University, College of Engineering, Trivandrum, Kerala, India

Abstract- Stock market index is a statistical measure that quantifies the changes in a portfolio of stocks which represents a portion of the overall stock market. Prediction of stock market has been a challenging task and of great interest for scholars as the very fact that stock market is a highly volatile in its behaviour. Prediction of stock market is substantial in finance and is gathering more attention, due to the verity that if the direction of the market is predicted successfully the investors may be effectively guided.”
“Deep Learning technique is a subfield of machine learning which is concerned with algorithms necessitated by the function and structure of the brain called artificial neural networks. The most popular techniques are Multilayer Perceptron Networks, Restricted Boltzmann Machines, Convolutional Neural Networks and Long Short-Term Memory Recurrent Neural Networks.”
“This work focuses on the task of predicting the stock market Index. The objective of the project work is to develop and compare the performances of Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) Networks in forecasting stock market indices. Recent ten years historical data of Bombay Stock Exchange (BSE) Sensex from the Indian Stock market has been chosen for the experimental evaluation. The Adam Optimizer is used for the training of deep neural networks. Root mean square Error (RMSE) is used to compare the performance of the prediction models. As seen from the results, the prediction is fairly accurate in both cases and MLP has outperformed LSTM model, in predicting stock market indices. Neural networks have proved to be a good technique, to forecast a chaotic time series data like stock market index.”

Keywords: Stock market index, Deep Learning, Multilayer Perceptron, Long Short-Term Memory Networks, Neural networks.

I. INTRODUCTION

The task of prediction of stock market is very challenging and of great interest for researchers as the very fact that stock market is a highly volatile in its behaviour. Prediction of stock market is substantial in finance and it is drawing more attention, due to the fact that the investors may be better guided if the direction and trend of the stock market is predicted successfully.





Subscribe to Our Newsletter

Sign up for our newsletter, to get updates regarding the Call for Paper, Papers & Research.