A Comparative Analysis of Machine Learning And Deep Learning Models For Predicting Stock Market Close Prices

Stock price prediction is inherently challenging due to the volatile and nonlinear nature of financial markets. Traditional financial models often fail to capture these complexities, but advancements in machine learning (ML) and deep learning (DL) offer promising solutions. This study evaluates the performance of ML models (KNN, Linear Regression, Random Forest) and DL models (ANN, RNN, LSTM) in predicting stock closing prices using daily Open, High, and Low prices as inputs. The analysis focuses on American Airlines (AAL) and Delta Airlines (DAL) datasets, representing low and high volatility, respectively. Model performance is assessed using MSE, MAE, and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> metrics. Results demonstrate that DL models, particularly LSTMs, outperform traditional ML models and exhibit strong adaptability across volatility levels.