Research of the Prediction of Stock Market Price Trends Based on Several Models

DOI

10.2991/978-94-6463-748-9_25How to use a DOI?

Keywords

Stock market prediction; machine learning; financial forecasting

Abstract

The property market is an important part of the world’s money system, and being able to determine how stock prices may walk is essential for making wise investment choices. Because stock markets can change quickly and are complicated, traditional methods often do not give accurate predictions. This research looks at innovative ways to determine stock marketplace price trends. It focuses on strategies like AutoRegressive Integrated Moving Average (ARI-MA), Random Trees, and Long Short-Word Storage (LSTM) neural networks. Using earlier inventory value data, we checked how well these concepts worked by looking at accuracy methods like Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). This helped us discover how great they were at understanding the complex patterns in stock prices. The findings show that LSTM, a type of deep learning model, works better than traditional quantitative methods. It is great at understanding extended-term connections and dealing with difficult relationships in unpredictable markets. Machine learning designs like Random Forests are great at recognizing quick-term trends, but ARIMA works well for data that is stable or follows a design over time. However, there are still issues like changing market conditions, the risk of concepts fitting too tightly to previous information, and the need for excel-lent quality information in all methods. The research shows that using various methods can increase the accuracy of estimating stock price changes. This helps traders make better decisions in altering market conditions.

Copyright

© 2025 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  - Ruoye Zhang
PY  - 2025
DA  - 2025/07/03
TI  - Research of the Prediction of Stock Market Price Trends Based on Several Models
BT  - Proceedings of the 2025 International Conference on Financial Risk and Investment Management (ICFRIM 2025)
PB  - Atlantis Press
SP  - 209
EP  - 217
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-748-9_25
DO  - 10.2991/978-94-6463-748-9_25
ID  - Zhang2025
ER  -