Predicting S&P 500 Prices Using Machine Learning
Seattle University
Jan 2019 - May 2019 (5 months)
Collected historical S&P 500 data from Yahoo Finance, including open/close prices, volume, and technical indicators.
Cleaned and normalized data; handled missing values and created lag features for time series modeling.
Built and tested multiple models: Linear Regression, ARIMA, and LSTM neural networks.
Evaluated model performance using RMSE and MAE; LSTM showed the best performance in trend prediction.
Used Python with libraries such as Pandas, NumPy, Scikit-learn, and Matplotlib.