Cryptocurrency is a digital asset that has been historically volatile. This volatility allows traders to capitalize on short term price movement. More specifically, cryptocurrency is vulnerable to “epidemic-like price bubbles” from social media factors compared to traditional assets (Phillips, 2018). Social media's influence on the price of cryptocurrency gives traders a unique opportunity for predicting price movements. Traditionally, traders have used technical analysis to predict the best opportunities to buy and sell, but sentiment analysis of posts on social media can help improve their accuracy. While humans are capable of manually conducting technical analysis, it is near impossible for them to understand the trends and consensus of an asset from posts on social media. A computer can conduct both technical and sentiment analysis more efficiently and use them as indicators to make accurate predictions on future price movements. The goal of this project is to create an automated trading program that uses technical and sentiment analysis as inputs for a machine learning model which can predict profitable opportunities to buy and sell cryptocurrency.

• 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

• Dandeneau, Sean P.
• Knight, Dante J.
• Gerulskis, Jack F.

Publisher

• Worcester Polytechnic Institute

Identifier

• E-project-040621-122122
• 17141

Stichwort

• Cryptocurrency
• Machine Learning
• Trading Program
• Sentiment Analysis

Advisor

• Smith, Therese Mary

Year

• 2021

Date created

• 2021-04-06

Resource type

• Major Qualifying Project

Major

• Computer Science

Rights statement

• In Copyright

Zuletzt geändert

• 2021-05-03