This study aims to predict stock price movements within the
sports industry on the
Tehran Stock Exchange (TSE) using advanced
machine learning (ML) algorithms. In recent years, the increasing complexity and volatility of emerging markets like Iran have intensified the need for accurate forecasting models, particularly in niche sectors such as the sports industry. The research employs historical stock price data, technical indicators, and macroeconomic variables as input features to train and validate several ML models, including Support Vector Machines (SVM),
Random Forest (RF), Gradient Boosting (GB), and Long Short-Term Memory (LSTM) networks. The study compares the models’ performances using metrics such as accuracy, precision, recall, and RMSE to determine the most effective algorithm for stock prediction in this sector. Feature selection and dimensionality reduction techniques, such as Principal Component Analysis (PCA), are also incorporated to improve model efficiency and avoid overfitting. Findings indicate that
LSTM networks demonstrate superior performance due to their ability to capture temporal dependencies in time-series data. The research provides valuable insights for investors, financial analysts, and policymakers seeking to enhance decision-making and risk management in sports-related financial instruments within the Iranian capital market.
پاسخ به دیدگاه