Is this project an undergraduate, graduate, or faculty project?

Undergraduate

group

What campus are you from?

Daytona Beach

Authors' Class Standing

Marissa Murphy, Senior Naomi Rodriguez, Senior Aaron Morgado, Senior Mason Gawler, Senior

Lead Presenter's Name

Marissa Murphy

Faculty Mentor Name

Dr. Khem Poudel

Abstract

Digital currency has recently gained popularity as it has become increasingly dependent on computers and the Internet. New forms of currency have been constantly evolving over the past few years, namely cryptocurrency. Virtual forms of currency have open new doors within the software industry in finance, data storage, and data collection. Cryptocurrency (crypto) is very volatile in terms of market value, which carries a host of unknowns that make it difficult to predict and analyze the future prices of crypto. However, cryptocurrency behaves similarly to stocks, which allows for the use of linear regression models to make predictions about price levels. With the ability to predict crypto prices, one can make a prediction for crypto stocks since the popular coin, Bitcoin, affects stock prices. This paper will discuss the use of two types of linear regression models, least squares and auto regression, as well as predictors such as social media and economic data to calculate the volatility of a given cryptocurrency and its prices. Using high performance computing techniques will allow regression models to predict relatively accurate crypto prices and past available cryptocurrency price data will be used to verify our results.

Did this research project receive funding support from the Office of Undergraduate Research.

No

Share

COinS
 

Cryptocurrency Price Predictions Using High Performance Computing

Digital currency has recently gained popularity as it has become increasingly dependent on computers and the Internet. New forms of currency have been constantly evolving over the past few years, namely cryptocurrency. Virtual forms of currency have open new doors within the software industry in finance, data storage, and data collection. Cryptocurrency (crypto) is very volatile in terms of market value, which carries a host of unknowns that make it difficult to predict and analyze the future prices of crypto. However, cryptocurrency behaves similarly to stocks, which allows for the use of linear regression models to make predictions about price levels. With the ability to predict crypto prices, one can make a prediction for crypto stocks since the popular coin, Bitcoin, affects stock prices. This paper will discuss the use of two types of linear regression models, least squares and auto regression, as well as predictors such as social media and economic data to calculate the volatility of a given cryptocurrency and its prices. Using high performance computing techniques will allow regression models to predict relatively accurate crypto prices and past available cryptocurrency price data will be used to verify our results.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.