CapitalVX: A Machine Learning Model for Startup Selection and Exit Prediction

13 Pages Posted: 21 Oct 2020

See all articles by Greg Ross

Greg Ross

Independent Researcher

Daniel Sciro

Venhound LLC

Sanjiv Ranjan Das

Santa Clara University - Leavey School of Business

Hussain Raza

Santa Clara University

Date Written: September 1, 2020

Abstract

Using a big data set of venture capital financing and related startup firms from Crunchbase, this paper develops a machine-learning model called CapitalVX (for “Capital Venture eXchange”) to predict the outcomes for startups, i.e., whether they will exit successfully through an IPO or acquisition, or fail. Using a large feature set, the out-of-sample accuracy of predictions on startup outcomes and follow-on funding is 88%. This research suggests that VC/PE firms may be able to benefit from using machine learning to screen potential investments using publicly available information, diverting this time instead into mentoring and monitoring the investments they make.

Keywords: machine learning, venture capital, success prediction

JEL Classification: C45, G24

Suggested Citation

Ross, Greg and Sciro, Daniel and Das, Sanjiv Ranjan and Raza, Hussain, CapitalVX: A Machine Learning Model for Startup Selection and Exit Prediction (September 1, 2020). Available at SSRN: https://ssrn.com/abstract=3684185 or http://dx.doi.org/10.2139/ssrn.3684185

Greg Ross

Independent Researcher

Daniel Sciro

Venhound LLC ( email )

10580 N McCarran Blvd
Suite 115 - 153
Reno, NV 89503
United States

Sanjiv Ranjan Das (Contact Author)

Santa Clara University - Leavey School of Business ( email )

Department of Finance
316M Lucas Hall
Santa Clara, CA 95053
United States

HOME PAGE: http://algo.scu.edu/~sanjivdas/

Hussain Raza

Santa Clara University ( email )

500 El Camino Real
Santa Clara, CA 95053
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
158
Abstract Views
536
rank
215,060
PlumX Metrics