This paper aims to investigate how Neural Network can be used to predict stock market as one of the fundamental challenges in financial Markets. To this end, this study uses different deep learning architectures to predict the prices of Tesla stock historical market data. Four neural network models were put into practice and compared: Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Standardized price and volume data from sixty-day sequences were used to train the models. To evaluate the models’ performances, we used the Mean Squared Error (MSE), the Root Mean Squared Error (RMSE) and the Mean Absolute Error (MAE). Our results show that RNN and LSTM performed noticeably better than other architectures, with comparable RMSE values of 0.0219 and 0.0231 and minimal MSE of 0.0005, respectively. These results were noticeably better than those of implementations of CNN (MSE: 0.0022) and ANN (MSE: 0.0092). The study shows that recurrent architecture offers a significant advantage in stock price prediction due to their capacity to capture temporal dependencies in financial time series data. This study adds to the increasing amount of data demonstrating the effectiveness of deep learning techniques in financial forecasting while emphasizing how crucial model architecture is to model performance.