Predictive Modeling of Apple Share Prices: A Comparative Study of Deep Learning Techniques

Abstract

This study examines stock market analysis through computational models to forecast stock price fluctuations, with a specific emphasis on the AAPL dataset from Apple Inc. This model is known for its ability to deal with long-term and sequential data. Due to these reasons, LSTM is the best model to deal with stock pricing predictions. Data preprocessing in this model includes time-series formatting, feature scaling, and the creation of sequential datasets. This model is trained by 80% of data and tested by 20% of data and been evaluated by (MAE), (MSE) to know its performance the result indicates that the model’s performance is well and makes a good prediction with accuracy 93% using 100 epochs to train the model in neural network. This model offers effective stock price prediction and a smart strategy for it. This model solved the problem of stock price prediction effectively.