Author(s):
1. Kashaf Gull:
Department of mathematics, Namal university Mianwali,,Pakistan
Abstract:
Aim of this study is to evaluate and compare the performance of different Ml model such as Random Forest, XGBoost, Regression and Classification model. Three datasets of Pakistan stock Exchange companies (AI-Abid Silks Mill limited, AI-Abbas Sugar Mill limited, and AI-Ghazi Tractor limited) including feature (Date, Open, Close, High, Low and Volume) are used to compare the performance the ML models. Among the four models Random Forest model achieved 1.0792 RMSE and 59.7% accuracy for AI Abid silk mills and XGBoost achieved 1.098 RMSE and 63.55% accuracy, regression model achieved 4.186 RMSE and classification model achieved highest accuracy 76.55%.Random Forest model achieved 9.494 RMSE and 53.79% accuracy for AI Abbas Sugar mills and XGBoost achieved 9.474 RMSE and 55.72% accuracy, regression model achieved 44.04 RMSE and classification model achieved highest accuracy 71.46%. Random Forest model achieved 13.489 RMSE and 50.8% accuracy for AI Ghazi Tractor Limited mills and XGBoost achieved 13.585 RMSE and 52.6% accuracy, regression model achieved 12.841 RMSE and classification model achieved highest accuracy 71.7%. Among the four ML models, Random Forest and XGBoost models achieved the lowest root mean squared error for AI Abid silk mills and for AI Abbas Sugar mills then AI Ghazi Tractor Limited data, RMSE value is used to evaluate the performance of Models, lowest RMSE show well working of ML models. Prediction of the model can help the sellers in identifying the best time to sell and enable brokers to develop informed trading strategies.
Page(s):
103-103
DOI:
DOI not available
Published:
Journal: 4th International Conference of Sciences “Revamped Scientific Outlook of 21st Century, 2025” , November 12,2025, Volume: 1, Issue: 1, Year: 2025
Keywords:
Regression
,
Classification
,
Accuracy
,
Random Forest
,
Machine learning
,
Trading Strategies
,
XGBoost
,
Pakistan Stock Exchange
,
RMSE
,
stock market prediction
References:
References are not available for this document.
Citations
Citations are not available for this document.