This Interactive Qualifying Project explored how historical behavior of the stock market can be used to predict future behavior of the stock market. The advantages and disadvantages of different trading strategies were reviewed, which led to selecting three strategies to implement in the study: momentum trading, day trading, and swing trading. Each contributing student developed a programmed-trading model based on one of these stock trading strategies to test the validity of our hypothesis over an 8-week simulation period. At the end of the simulation, the performance of the models were analyzed and compared. The simulations resulted in the momentum trading strategy profiting 1.26%, the swing trading strategy profiting 1.96%, and the day trading strategy profiting a remarkable 20.35%.

• 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

• Rathi, Ishan
• Anand, Rohan
• Roskind, Brianna

Subject

• Industry
• Project-Based Learning
• Innovation
• Computing
• Learning

Publisher

• Worcester Polytechnic Institute

Identifier

• 68166
• E-project-050422-170635

Keyword

• Convolutional Neural Network
• Machine Learning
• Deep Learning
• Technical Analysis
• Recurrent Neural Network
• Fundamental Analysis

Advisor

• Tang, Dalin

Year

• 2022

UN Sustainable Development Goals

• 8 - Decent Work and Economic Growth

Date created

• 2022-05-04

Resource type

• Interactive Qualifying Project

Rights statement

• In Copyright