Qinyi Lin

How can historical stock data from 2010 to 2016 for Apple, combined with various variables, be used to train a neural network for forecasting future stock prices by implementing a Python script?

Started May 8, 2023

Abstract or project description

This research aims to predict the future stock prices of Apple Inc. by utilizing historical stock data from 2010 to 2016, combined with multiple variables including financial metrics (e.g., Period Ending, Additional income/expense items, Capital Expenditures, Capital Surplus, Cash Ratio), stock market indicators (e.g., open, close, low, high, volume), and even the performance of related companies. Python scripts will be implemented to analyze a comprehensive dataset obtained from the New York Stock Exchange (NYSE) and develop a sophisticated prediction model using advanced statistical techniques and machine learning algorithms. The Python scripts will automate the model to achieve efficient and accurate predictions. The developed model will be evaluated using robust metrics such as Mean Squared Error (MSE). Stochastic Gradient Descent (SGD) will be used to train the model. By leveraging these comprehensive categories of variables, this research aims to provide a valuable tool for investors and financial analysts to make informed decisions in the dynamic Apple stock market environment.