LSTM-Based Temporal Analysis of Nifty 50: Accuracy Dynamics across Varied Time Frames

DOI

10.2991/978-94-6463-471-6_111How to use a DOI?

Keywords

Stock Market Prediction; Long Short-Term Memory (LSTM); Data Noise; Financial markets; Long-term dependencies

Abstract

Given the inherent noise and volatility in financial markets, accurate stock market price prediction is still a difficult task. In this work, the Investigation of Long Short-Term Memory (LSTM) models for stock price prediction in the face of varied levels of noise in various historical data time frames is carried out. Because of LSTM has reputation for capturing long-term dependencies, and these (LSTMs) are used to navigate the complex and noisy world of stock market dynamics. Several financial indicators and past stock prices are included in this set, which is pre-processed to account for the noise that is always present in financial data. The data is arranged temporally over a variety of intervals, from daily to monthly, which enables one to examine the flexibility of the LSTM model over a range of time periods. The study measures the predictive accuracy, precision, and recall of the LSTM model by methodically analysing its performance in the presence of data noise. The robustness of the model in both short- and long-term prediction situations receives particular consideration. Moreover, the influence of combining different technical indicators and outside variables is investigated to determine how well they work to reduce noise and improve forecast accuracy. This work recognises and addresses the ubiquitous noise in financial datasets, adding to the sophisticated knowledge of LSTM models in the context of stock market prediction. The results of this study demonstrate the LSTM are effective for stock price prediction the LSTM model has yielded an R2-score of 1 and Root Mean Squared Error (RMSE) value of 27.93.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Priyanka Dash
AU  - Jyotirmaya Mishra
AU  - Suresh Dara
PY  - 2024
DA  - 2024/07/30
TI  - LSTM-Based Temporal Analysis of Nifty 50: Accuracy Dynamics across Varied Time Frames
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 1164
EP  - 1172
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_111
DO  - 10.2991/978-94-6463-471-6_111
ID  - Dash2024
ER  -