Effect of Deep Learning on Stock Price Analysis and Forecasting

This project (case study) examines the applications of deep learning in financial data analysis and forecasting. The main goal of this project is to evaluate the potential of deep learning models for stock price prediction and to improve financial decision-making.  

Deep learning algorithms can improve the performance of an investor’s trading activities in the stock market. This project aims to evaluate the potential of deep learning techniques to create models for accurate market forecasting and analyze the complexities of the trading market to help investors make better decisions.  

The project will identify and assess the need for data science action by working with large stock market datasets, handling non-linear data, evaluating performance, and analyzing prediction accuracy 

The data for this case study is sourced from Apple Inc. via Yahoo Finance, covering the period from March 30, 2020, to March 30, 2025. The dataset includes historical time-series data, with columns such as Date, Open, High, Low, Close, Adjusted Close, and Volume. 

The study evaluates four deep learning models: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN), and compares their performance to traditional machine learning models such as Decision Tree and Random Forest. Key evaluation metrics include Root Mean Square Error (RMSE) and Mean Absolute Error (MAE).  

Project Objectives: 

1-Analyzing the Optimization of Deep Learning Techniques in Trading Processes in the Stock Market 

2-Evaluating the Effectiveness of Deep Learning in Trend Analysis for Stock Price Forecasting 

3-Assessing Prediction Accuracy