Stock Price Prediction Using LSTM Based DL Model and its Comparison with ML Algorithms

Predicting stock prices is an essential component of financial market analysis since it provides information that can help with risk management and investing choices. Deep learning's (DLs) strong processing capabilities and capacity to comprehend intricate, non-linear interactions have shown considerable promise in stock price prediction. This study uses a Long Short-Term Memory (LSTM)-based model to predict stock values. It evaluates how well it performs in comparison to more conventional machine learning (ML) algorithms like random forests (RF) and linear regression (LR). To thoroughly assess the models, the following performance matrices will be considered: accuracy, precision, recall, and F1-score. These metrics offer a comprehensive assessment of the predictive accuracy, robustness, and generalization capacities of the models. Our results show that, whereas classic ML methods can provide fast and easily interpreted results, the LSTM-based model performs better at capturing the complex temporal patterns present in stock price data. The comparative research highlights how DL can improve the accuracy of stock price predictions, giving important new information to financial analysts and investors. Our proposed LSTM model achieves 15.78 % higher accuracy than LR and 6.91 % higher accuracy than RF, demonstrating its superior performance in stock price prediction.