Comparative analysis of time-series forecasting algorithms for stock price prediction

Baleshwarsingh Joosery, G. Deepa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper predicts the average stock price for five datasets by utilizing the historical stock price data ranging from April 2009 to February 2019. Autoregressive Integrated Moving Average (ARIMA) model is used to generate the baseline, while Long Short-Term Memory (LSTM) networks is used to build the forecasting model for predicting the stock price. The efficiency of the two models is compared in terms of Mean Squared Error. The results show that the LSTM model predicts better than the ARIMA model with respect to time series forecasting. Additionally, Attention LSTM networks is employed to further study the improvement in accuracy of the stock price forecasting model.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Advanced Information Science and System, AISS 2019
PublisherAssociation for Computing Machinery (ACM)
ISBN (Electronic)9781450372916
DOIs
Publication statusPublished - 15-11-2019
Externally publishedYes
Event2019 International Conference on Advanced Information Science and System, AISS 2019 - Singapore, Singapore
Duration: 15-11-201917-11-2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2019 International Conference on Advanced Information Science and System, AISS 2019
CountrySingapore
CitySingapore
Period15-11-1917-11-19

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'Comparative analysis of time-series forecasting algorithms for stock price prediction'. Together they form a unique fingerprint.

Cite this