The US stock market is often divided into 11 sectors. Among them, the energy sector and the consumer staples sector were selected as the focus of this project. The first goal was to forecast short-term stock prices based on historical stock prices and relevant market indices. The second goal was to detect future major index fluctuations of the Dow Jones index. Methods included autocorrelation, Fourier series analysis, local linear regression, principal component analysis, Multi Factor models and Gibbs phenomena analysis.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Busaranuvong, Palawat
• Mao, Dan

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-101020-041347
• 4361

Keyword

• Multi Factor models
• Gibbs phenomena analysis
• US stock market
• Principal component analysis
• Fourier series analysis
• Local linear regression

Advisor

• Humi, Mayer

Year

• 2020

Date created

• 2020-10-10

Resource type

• Major Qualifying Project

Major

• Mathematical Sciences

Rights statement

• In Copyright

License

• Creative Commons BY-NC Attribution-NonCommercial 4.0 International