Date of Award

5-2018

Degree Type

Thesis

Degree Name

Departmental Honors

Department

Computer Science

Abstract

This project takes several common strategies for algorithmic stock trading and tests them on the cryptocurrency market. The three strategies used are moving average crossover, mean reversion, and pairs trading. Data was collected every five minutes for the top one hundred cryptocurrencies between October 5, 2017, and January 24, 2018. Due to the high volatility of the market, the data includes various market situations. Three noted situations are a rising market, falling market, and relatively stable market. The three strategies were modified to optimally follow each market situation. Modifications include adjusting parameters used in each strategy as well as mixing several strategies or dynamically changing between strategies. In each strategy and with each cryptocurrency, the benchmark against which the algorithm is tested is the market's performance, or what an investor would have after buying and holding. Returns are compared with the buying and holding strategy, and different scenarios are analyzed to determine the risk associated with buying and holding compared with an algorithmic strategy. Results will be taken with the market's actual trends and also with some alternate possible trends to test all market scenarios. A web interface will accompany the presentation, allowing users to test the strategies by entering their own parameters and instantly see the results.

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .

 

Faculty Mentor

Andrew Brim

Departmental Honors Advisor

Dean Adams