Document Type

Thesis or dissertation

Date of this Version



Pinar Yildirim


Equity crowdfunding is an increasingly popular means of raising capital for early stage startups. It enables entrepreneurs to finance their companies with smaller contributions from a variety of people. This paper studies the relationship between the characteristics of a given company and its ability to raise funds on an equity crowdfunding platform. A series of statistical and machine learning models are fit to data from a U.S.-based equity crowdfunding website, including a logistic regression, a CART decision tree, a naïve Bayes classifier, and a support vector machine. This study demonstrates that a connection exists between the probability of a company’s crowdfunding success and its previous funding history, Twitter presence, media buzz, size, location, and its founders’ educational backgrounds. As a whole, however, the classification quality of the various models leaves something to be desired. This suggests the need for additional data inputs and more longitudinal research in the field of equity crowdfunding.


venture capital, equity crowdfunding, machine learning

Included in

Business Commons



Date Posted: 10 August 2016


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.