Saved in:
Bibliographic Details
Main Authors: Yu, Chang, Liu, Fang, Zhu, Jie, Guo, Shaobo, Gao, Yifan, Yang, Zhongheng, Liu, Meiwei, Xing, Qianwen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.23084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910973318660096
author Yu, Chang
Liu, Fang
Zhu, Jie
Guo, Shaobo
Gao, Yifan
Yang, Zhongheng
Liu, Meiwei
Xing, Qianwen
author_facet Yu, Chang
Liu, Fang
Zhu, Jie
Guo, Shaobo
Gao, Yifan
Yang, Zhongheng
Liu, Meiwei
Xing, Qianwen
contents This paper proposes a hybrid framework combining LSTM (Long Short-Term Memory) networks with LightGBM and CatBoost for stock price prediction. The framework processes time-series financial data and evaluates performance using seven models: Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Bidirectional LSTM (BiLSTM), vanilla LSTM, XGBoost, LightGBM, and standard Neural Networks (NNs). Key metrics, including MAE, R-squared, MSE, and RMSE, are used to establish benchmarks across different time scales. Building on these benchmarks, we develop an ensemble model that combines the strengths of sequential and tree-based approaches. Experimental results show that the proposed framework improves accuracy by 10 to 15 percent compared to individual models and reduces error during market changes. This study highlights the potential of ensemble methods for financial forecasting and provides a flexible design for integrating new machine learning techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23084
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gradient Boosting Decision Tree with LSTM for Investment Prediction
Yu, Chang
Liu, Fang
Zhu, Jie
Guo, Shaobo
Gao, Yifan
Yang, Zhongheng
Liu, Meiwei
Xing, Qianwen
Machine Learning
This paper proposes a hybrid framework combining LSTM (Long Short-Term Memory) networks with LightGBM and CatBoost for stock price prediction. The framework processes time-series financial data and evaluates performance using seven models: Artificial Neural Networks (ANNs), Convolutional Neural Networks (CNNs), Bidirectional LSTM (BiLSTM), vanilla LSTM, XGBoost, LightGBM, and standard Neural Networks (NNs). Key metrics, including MAE, R-squared, MSE, and RMSE, are used to establish benchmarks across different time scales. Building on these benchmarks, we develop an ensemble model that combines the strengths of sequential and tree-based approaches. Experimental results show that the proposed framework improves accuracy by 10 to 15 percent compared to individual models and reduces error during market changes. This study highlights the potential of ensemble methods for financial forecasting and provides a flexible design for integrating new machine learning techniques.
title Gradient Boosting Decision Tree with LSTM for Investment Prediction
topic Machine Learning
url https://arxiv.org/abs/2505.23084