Apple_Stock_Prediction

Stock market financial advisors often require trends to determine if a stock should be traded as a future, option, forward, swap or another financial instrument. This project analyzes the auto regressive integrated moving average (ARIMA), long short-term memory (LSTM), gated recurrent unit (GRU) and ARIMA-LSTM hybrid models' ability to forecast Apple’s current opening day stock price. Model hyperparameters are tuned using Bayesian optimization. Root mean square error (RMSE), mean absolute error (MAE) and mean forecast error (MFE) are the accuracy measures used for model analysis. Results of analysis show that the ARIMA-LSTM hybrid model is the most accurate followed by GRU, LSTM and ARIMA models.