CFP last date
21 October 2024
Reseach Article

Prediction of Stock Market Returns using LSTM Model and Traditional Statistical Model

by Seth Gyamerah, Dennis Redeemer Korda
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 183 - Number 37
Year of Publication: 2021
Authors: Seth Gyamerah, Dennis Redeemer Korda
10.5120/ijca2021921773

Seth Gyamerah, Dennis Redeemer Korda . Prediction of Stock Market Returns using LSTM Model and Traditional Statistical Model. International Journal of Computer Applications. 183, 37 ( Nov 2021), 57-61. DOI=10.5120/ijca2021921773

@article{ 10.5120/ijca2021921773,
author = { Seth Gyamerah, Dennis Redeemer Korda },
title = { Prediction of Stock Market Returns using LSTM Model and Traditional Statistical Model },
journal = { International Journal of Computer Applications },
issue_date = { Nov 2021 },
volume = { 183 },
number = { 37 },
month = { Nov },
year = { 2021 },
issn = { 0975-8887 },
pages = { 57-61 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume183/number37/32175-2021921773/ },
doi = { 10.5120/ijca2021921773 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:18:57.951171+05:30
%A Seth Gyamerah
%A Dennis Redeemer Korda
%T Prediction of Stock Market Returns using LSTM Model and Traditional Statistical Model
%J International Journal of Computer Applications
%@ 0975-8887
%V 183
%N 37
%P 57-61
%D 2021
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Despite the growing interest in time series data specifically, stock market predictions in the financial world as well as its development stages of most related studies, this article aim to provide a good structure and suitable model for predicting the trend movement of stock market returns. This is done through a classification wavelet LSTM network model and the result compare to a baseline model. The results show that there are high returns of S&P500 stock market prices with a 15minutes interval range as compared to the wavelet-logistic (W-LR) regression model. It is therefore obvious that the enhanced deep neural network (W-LSTM, LSTM model) performs better in stock market prediction as compared to the traditional statistical models (LR W-LR).

References
  1. Gyamerah, S., & Awuah, A. Trend forecasting in financial time series with indicator system. J. Appl. Stat, 0-14.
  2. Korda, D. R., Agoha, S. A., & Haruna, D. A. (2017). Stock trend forecasting using regression analysis. [Unpublished manuscript]. Department of Computer Science, University of Cape Coast.
  3. Vijag Kotu; Deshgande, in data science edition (2019) using ARIMA models for financial time series predictions, Science Direct.
  4. Kelvin Li and Glen Yu (2000), Deep Learning for stock price forecasting. Journal of machine learning.
  5. Jiang Q, Tang C, Chen C, et al. Stock Price Forecast Based on LSTM Neural Network [ 2018] computing and application journal
  6. Liu Y, Guon, LHou,C Hau, H;Liu , Jun, Y, Zheng, M. wind power short-term prediction based on LSTM and discrete wavelet transform (2012) journal Machine learning 1108.
  7. Liu Huicheng. Leveraging Financial News for Stock Trend Prediction with Attention-Based Recurrent Neural Network (2018) Journal of science and informatics.
  8. Tay F.E.H. Cao L application of support vectors machine in financial time series forecasting (2007) journal of university of electronic science and technology, 29(4)-309-337
  9. Lee, M.C. using support vector machine with a hybrid feature selection method to stock trend prediction. Expert system, Appl (2009), 36,10896-10904
  10. H.Suchi, T. J Hsiao, H.F., Yeh W.C. Forecasting stocks market using wavelet transform and recurrent neural networks, an integrated system based on artificial bee colony algorithm 2011) Appl. Software computing 11,2510-2525
  11. Erban Beyaz, Firat Tekiner, Xiao-jun Zeng, john A.Keane(2018) comparing technical and fundamental indicators in stock price forecasting. International conference on High performance computing and communication, IEE 16th conference on smart city.
  12. Rajashree, Dash and Pradipta Kishone Dash (March,2016). A hybrid stock trading framework integrating technical analysis with machine learning techniques. The Journal of finance and Data science 2(2016) 42-57.
  13. Francisco J.Ruiz, Alberta Jama, German Sanchez, Jose A. Sanabria and Nuna Agell(2011) An interval technical indicators for financial time series forecasting .Journal of statistical software, vol.
  14. Weihong Huang and Yu Zhang (June 31,2014) Asymmetry Index of stock price fluctuations. Journal of Global Economics
  15. Basit Janvir, khan Moman Jarel etc (August 2017) Evolving Technical Trading strategies using Genetic Algorithms. A case study of Pakistan stock exchange. Conference Paper: IDEAL 2017
  16. Fiu Feng, Xiangnan He, Xiang Wnag etc (March, 2018) Temporal Relational Banking for stock prediction. Journal of HCM transactions information system 37(2) 1-30
  17. Tobias Schadler (Dec,25,2018) Measuring irrationality in financial markets. A chieves Business Research Vol.6 No.12
  18. Gary R Weckmen, Siriam Lakshminarayanan (May2004) Identify technical indicators for stock market prediction with Neural Network. Conferences: proceedings of the IIE Annual Conference.
Index Terms

Computer Science
Information Sciences

Keywords

LSTM model Logistic regression model Stock market (S&P500) and classification problem Wavelet transform function.