PROJECT TITLE: PREDICTING STOCK EXCHANGE TRENDS USING MACHINE LEARNING, DEEP LEARNING TECHNIQUES

Abstract

Predicting stock market trends remains a challenging task due to the volatile and nonlinear nature of financial data. This study explores the application of machine learning and deep learning techniques to forecast stock price movements using historical data from the Tehran Stock Exchange. We evaluate nine machine learning models—Decision Tree, Random Forest, Adaboost, XGBoost, SVC, Naive Bayes, KNN, Logistic Regression, and ANN—and two deep learning models—RNN and LSTM. The models are trained on ten technical indicators derived from ten years of data, applied in both continuous and binary formats. Experimental results demonstrate that LSTM and RNN outperform traditional models, especially when using binary data. The study also presents a modular web-based system built using Python, Flask, and MySQL to facilitate real-time trend prediction.