LSTM Neural Network in Stock Price Prediction

DOI

10.2991/978-94-6463-198-2_87How to use a DOI?

Keywords

machine learning; stock price prediction; long short-term memory; neural network

Abstract

Being an important part of the national economy, the stock market has always performed an important role in economic development. Following the growth of the times and variations in the investment philosophy of people, an increasing number of people have become involved in the stock market and predicting stock prices has become a popular topic. Stock prices are a kind of time series data, it has a large amount of data, high variability, high noise, and volatility, thus the traditional statistical analysis methods cannot properly capture the characteristics of these non-linear data and resulting in poor prediction accuracy. LSTM is a type of recurrent neural network, and it has become an effective learning model to deal with time series data. This paper will focus on LSTM neural networks and investigate the effect of the memory length for past data on the accuracy of the model prediction. In the experiments, the model prediction results will be compared using data from the past day, past week, past month, and the past year as inputs. The results show that the best predictions are made using short-term past data as input, particularly when using data from the past day as input.

Copyright

© 2023 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  - Kejia Zhang
PY  - 2023
DA  - 2023/08/10
TI  - LSTM Neural Network in Stock Price Prediction
BT  - Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
PB  - Atlantis Press
SP  - 848
EP  - 856
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-198-2_87
DO  - 10.2991/978-94-6463-198-2_87
ID  - Zhang2023
ER  -