Enhancing the Accuracy of Apple Stock Rise and Fall Prediction Based on News Sentiment Analysis and Multi-Factor Model

DOI

10.2991/978-94-6463-823-3_75How to use a DOI?

Keywords

Stock Prediction; Sentiment Analysis; Apple Stocks

Abstract

As one of the leading tech companies, Apple Inc. Gets worldwide attention, and any news related to it may cause market volatility. Based on the stock price data of Apple Inc. From 2006 to 2016 and the sentiment score of financial news, this study constructs a multi-dimensional feature system that integrates technical indicators and sentiment factors, and compares the prediction performance of four model on the rise and fall direction of the stock price on the T + 3 day to quantify the value of financial news. Experiments show that eXtreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) have the best performance, with the test set accuracy reaching 89.5% and 89.7% respectively, and Receiver Operating Characteristic Area Under Curve (ROC-AUC) exceeding 0.95. Long Short-Term Memory (LSTM) performs poorly (accuracy of 63.6%). Feature importance analysis reveals that sentiment trend and volatility sentiment are the key driving factors, which verifies the synergistic effect of sentiment and technical indicators. Research shows not only the significant advantages of ensemble learning models and both the potential and challenges of temporal models, but also the sentiment trend’s domination as well as the synergistic effect between technical indicators and sentiment.

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  - Mingliang Zhong
PY  - 2025
DA  - 2025/08/31
TI  - Enhancing the Accuracy of Apple Stock Rise and Fall Prediction Based on News Sentiment Analysis and Multi-Factor Model
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 761
EP  - 769
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_75
DO  - 10.2991/978-94-6463-823-3_75
ID  - Zhong2025
ER  -