The purpose of this project is to use data mining and big data analytic techniques to forecast daily stock market return with multiple linear regression. Using mathematical and statistical models to analyze the stock market is important and challenging. The accuracy of the final results relies on the quality of the input data and the validity of the methodology. In the report, within 5-year period, the data regarding eleven financial and economical features are observed and recorded on each trading day. After preprocessing the raw data with statistical method, we use the multiple linear regression to predict the daily return of the S&P 500 Index ETF (SPY). A model selection procedure is also completed to find the most parsimonious forecasting model.
Chen, Shengxuan, "Forecasting Daily Stock Market Return with Multiple Linear Regression" (2020). Mathematics Senior Capstone Papers. 19.