Scholarlink

<p>This research focuses on improving the accuracy of stock market trend prediction using ensemble learning and dimension reduction techniques. This study employs machine learning algorithms and dimension reduction methods on historical stock market data, specifically the TCS stock market dataset. Dimension reduction is achieved through min–max scaling and principal component analysis (PCA). An ensemble learning model is introduced that combines regression techniques such as LASSO regression, decision tree regression, K-neighbor regression, and random forest regression. Performance evaluation metrics, including the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), are used to validate the effectiveness of the model. The research demonstrates that the proposed ensemble learning model with dimension reduction techniques outperforms individual regression models, leading to enhanced accuracy in stock market forecasting. The use of explainable AI aids in improving the transparency of model outputs, providing insights into the influence of individual variables and facilitating a better understanding of the decision-making process. Despite the inherent volatility in stock market dynamics, the proposed designs exhibit robust predictive capabilities, offering practical and actionable insights. The study concludes that integrating diverse regression techniques through ensemble learning, along with dimension reduction methods, significantly improves the accuracy of stock price predictions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Utilizing Ensemble Learning and Dimension Reduction in Predicting Stock Prices: A Transparent Methodology with Insights from Explainable AI

  • 期刊论文

  • 发表日期：

    2025年1月17日

查看全文
  • Nabanita Das,
  • Bikash Sadhukhan,
  • Chayan Ghosh,
  • Avigyan Chowdhury,
  • Satyajit Chakrabarti

摘要

This research focuses on improving the accuracy of stock market trend prediction using ensemble learning and dimension reduction techniques. This study employs machine learning algorithms and dimension reduction methods on historical stock market data, specifically the TCS stock market dataset. Dimension reduction is achieved through min–max scaling and principal component analysis (PCA). An ensemble learning model is introduced that combines regression techniques such as LASSO regression, decision tree regression, K-neighbor regression, and random forest regression. Performance evaluation metrics, including the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE), are used to validate the effectiveness of the model. The research demonstrates that the proposed ensemble learning model with dimension reduction techniques outperforms individual regression models, leading to enhanced accuracy in stock market forecasting. The use of explainable AI aids in improving the transparency of model outputs, providing insights into the influence of individual variables and facilitating a better understanding of the decision-making process. Despite the inherent volatility in stock market dynamics, the proposed designs exhibit robust predictive capabilities, offering practical and actionable insights. The study concludes that integrating diverse regression techniques through ensemble learning, along with dimension reduction methods, significantly improves the accuracy of stock price predictions.