Authors:
Min Zayya, Min Kaung Khant, Win Htet Soe, Hlaing Htake Khaung Tin, Noe Hernández Hernández, Targyn A. Nauryz
Addresses:
Faculty of Information Science, University of Information Technology, Yangon, Yangon Region, Myanmar. Department of Engineering and Technology, Autonomous University of Tlaxcala, Santa Apolonia Teacalco, Tlaxcala, Mexico. International School of Economics, Kazakh British Technical University, Almaty, Kazakhstan.
Predicting the direction of stock prices is an intricate task due to the dynamism, non-linearity, and volatility of financial markets. This research compares machine learning models for predicting stock price direction using publicly available market data. We use historical stock market data, such as open, close, high, low, trading volume, and technical indicators, to build a binary classification framework that forecasts whether the stock price will increase or decrease in the next trading period. This study comparatively evaluates several machine learning models, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting. The models are evaluated using classification metrics such as accuracy, precision, recall, F1-score, and others. A standardized data preprocessing and evaluation process is employed to enable a fair comparison between the machine learning models. The study aims to identify the best-performing models and analyze the advantages and disadvantages of different machine learning methods for predicting stock market direction.
Keywords: Stock Price Prediction; Machine Learning; Stock Market; Direction Prediction; Classification and Technical Indicators; Public Market Data; Decision Tree; Random Forest.
Received on: 06/05/2025, Revised on: 15/08/2025, Accepted on: 02/11/2025, Published on: 05/06/2026
DOI: 10.69888/FTSTPL.2026.000809
FMDB Transactions on Sustainable Technoprise Letters, 2026 Vol. 4 No. 2, Pages: 60-71