Semiconductor Sector ETF Price Directional Prediction Based on Machine Learning Models

DOI

10.2991/978-94-6463-823-3_73How to use a DOI?

Keywords

Exchange-traded Mutual Fund; Machine Learning; Financial Market Prediction

Abstract

VanEck Semiconductor ETF(SMH) is one of the most liquid ETFs in America and has performed excellently over the past decade. This research aims to predict the direction of the price change of SMH five days later. The author trains Logistic Regression, Support Vector Machine (SVM), Random Forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Back Propagation Network (BPN) models to address this issue. In the first training section, it is found that SVM outperforms other individual models, with the highest test accuracy of 56.52% and the highest test AUC of 51.20%. In the second training section, more technical indicators are added. It is found that Random Forest has the best performance with a test accuracy of 56.64% among individual models. The voting model, which combines different predictions, achieves the highest test AUC of 58.76%. As evident from the results, technical indicators added as features can improve the prediction, with the operation of Principal Component Analysis (PCA). The findings of this research may help institutional and individual investors analyze market trends and make investment decisions.

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  - Yiguo Chen
PY  - 2025
DA  - 2025/08/31
TI  - Semiconductor Sector ETF Price Directional Prediction Based on Machine Learning Models
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 743
EP  - 752
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_73
DO  - 10.2991/978-94-6463-823-3_73
ID  - Chen2025
ER  -