Scholarlink

This study evaluates the performance of a random forest machine learning (ML) model in predicting and assessing financial risks in the Oil Gas & Consumable Fuels sector. Using the data from Yahoo Finance (January 15, 2015–January 25, 2025), a Random Forest model was trained to predict log returns and evaluated using performance metrics (MSE, RMSE, R2 and MAE). For each company, risk measures such as VaR, CVaR, Sharpe Ratio and Sortino Ratio were explored. Our findings show the potential of random forests, outperforming traditional models, and offering superior predictive accuracy and risk management. The study aims to build a system for predicting log returns and access risk using ML and provides insights highlighting the potential for improved stability and decision making.

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

Leveraging Machine Learning for Stock Returns Prediction and Risk Assessment in Stock Markets

  • 章节

  • 发表日期：

    2026年

查看全文
  • D. Vijayalakshmi,
  • S. R. Sahithyasree,
  • S. Jayashree

摘要

This study evaluates the performance of a random forest machine learning (ML) model in predicting and assessing financial risks in the Oil Gas & Consumable Fuels sector. Using the data from Yahoo Finance (January 15, 2015–January 25, 2025), a Random Forest model was trained to predict log returns and evaluated using performance metrics (MSE, RMSE, R2 and MAE). For each company, risk measures such as VaR, CVaR, Sharpe Ratio and Sortino Ratio were explored. Our findings show the potential of random forests, outperforming traditional models, and offering superior predictive accuracy and risk management. The study aims to build a system for predicting log returns and access risk using ML and provides insights highlighting the potential for improved stability and decision making.