Stock price prediction using machine learning: evidence from Pakistan stock exchange

This study explores the application of machine learning techniques to predict the movement of stock prices in the market. Using a dataset of historical stock prices (KSE-100 Index), a Random Forest classifier is employed to make predictions about whether a stock will rise or fall in the future. The model is trained using a sliding window approach and is evaluated using precision, recall, and F1-score metrics. The study also includes back testing and hyper-parameter tuning to improve the model's performance. The results show that the model achieves a precision score of 58%, an improvement from the previous score of 48%. However, the overall accuracy of the model is only 58%, indicating that further improvements are necessary. The study also suggests future directions for research, including the use of alternative data sources, sentiment analysis, and more sophisticated algorithms. The study's findings have implications for investors and financial organizations, demonstrating the potential of machine learning to make more educated investment decisions and enhance financial forecasting and analysis.