Date of Award

8-2020

Degree Type

Creative Project

Degree Name

Master of Science (MS)

Department

Economics and Finance

Committee Chair(s)

Tyler Brough

Committee

Tyler Brough

Committee

Pedram Jahangiry

Committee

Paul Fjeldsted

Abstract

This study develops and tests the hypothesis that the machine learning algorithm, Random Forests, can be used to systematically pick financial ratios that would be best for indicating market trends and be used subsequently to perform comparable analysis to speculate whether a firm is over- or under-valued. Results show that financial ratio selection differs depending on the market sector to which a firm pertains. We examine the 11 financial sectors representing the key areas of the economy. We also look at four possible trading strategies that an investor could have: month-long, quarter-long, semi-annual, and annual to capture differing trading horizons.

Included in

Finance Commons

Share

COinS