# Compare of Linear Regression Model and LSTM Neural Network in Machine Learning

### Yixuan Pan

#### 2024

#### Abstract

Stock forecasting involves analysts leveraging their profound knowledge of the stock market to predict the future trajectory of the stock market and the extent of price fluctuations based on the evolution of stock prices. This predictive activity relies solely on presumed factors and set conditions. Numerous investors employ mathematical models and algorithms to sift through vast datasets, producing stock price predictions. The adoption of machine learning and artificial intelligence technology in this domain is increasingly prevalent. Comparing linear regression models and Long Short-Term Memory Networks (LSTM) in stock market analysis involves evaluating their effectiveness in predicting stock trends. Linear regression, known for its simplicity and ease of interpretation, is suitable for datasets with linear relationships. However, it might not effectively capture complex patterns in financial markets. On the other hand, LSTM, a type of recurrent neural network, excels in handling time-series data and can model complex relationships by learning from long-term dependencies in the data. This makes LSTM more adept at understanding and predicting the often non-linear and volatile nature of stock prices, albeit at the cost of increased computational complexity and a need for more data.

Download#### Paper Citation

#### in Harvard Style

Pan Y. (2024). **Compare of Linear Regression Model and LSTM Neural Network in Machine Learning**. In *Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE*; ISBN 978-989-758-690-3, SciTePress, pages 218-223. DOI: 10.5220/0012871700004547

#### in Bibtex Style

@conference{icdse24,

author={Yixuan Pan},

title={Compare of Linear Regression Model and LSTM Neural Network in Machine Learning},

booktitle={Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE},

year={2024},

pages={218-223},

publisher={SciTePress},

organization={INSTICC},

doi={10.5220/0012871700004547},

isbn={978-989-758-690-3},

}

#### in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Science and Engineering - Volume 1: ICDSE

TI - Compare of Linear Regression Model and LSTM Neural Network in Machine Learning

SN - 978-989-758-690-3

AU - Pan Y.

PY - 2024

SP - 218

EP - 223

DO - 10.5220/0012871700004547

PB - SciTePress