EUVIMEDDescoperă EUVIMED
Crossref

Stock Market Prediction Time Series Analysis Using Stacked LSTM Model

Parnandi SrinuVasarao, Midhun Chakkaravarthy

SCIREA Journal of Computer · 2019

DOI: 10.54647/computer520418 ↗

At a glance

Journal article in SCIREA Journal of Computer, 2019. Written by Parnandi SrinuVasarao and 1 co-authors. Cited 1 times so far (Crossref).

RezumatDate bibliograficeCiteRelated studies

Abstract (original language)

Stock Market prediction has long been a challenging task due to its complex and dynamic nature. Time series analysis using Long Short-Term Memory(LSTM) neural network has merged as a promising approach for predicting stock prices. This research aims to investigate the effectiveness of LSTM models in predicting stock market trends and to explore their potential for generating actionable in sights for traders and investors. This study utilizes historical stock price data to train and evaluate LSTM models for predicting future stock prices, utilizing various hyperparameters and model configurations for optimal performance. The study demonstrates the effectiveness of LSTM-based time series analysis in stock market prediction, indicating its practical application for traders and investors in volatile markets, but acknowledges uncertainty and needs further research.

Cite

APA

SrinuVasarao, P., & Chakkaravarthy, M. (2019). Stock Market Prediction Time Series Analysis Using Stacked LSTM Model. SCIREA Journal of Computer. https://doi.org/10.54647/computer520418

Vancouver

SrinuVasarao P, Chakkaravarthy M. Stock Market Prediction Time Series Analysis Using Stacked LSTM Model. SCIREA Journal of Computer. 2019. doi:10.54647/computer520418

BibTeX
@article{SrinuVasarao2019,
  author = {SrinuVasarao, Parnandi and Chakkaravarthy, Midhun},
  title = {Stock Market Prediction Time Series Analysis Using Stacked LSTM Model},
  journal = {SCIREA Journal of Computer},
  year = {2019},
  doi = {10.54647/computer520418}
}
Start for free →