How Likely is the Investment of a Venture Capital Firm in a Latin American Country? Machine Learning Models Based on Experience, Distances and Network Features

The ability to accurately estimate whether a venture capital firm will invest in a region benefits investors, companies and investment promotion agencies. We applied machine learning techniques to make this prediction in Latin America, using firm, country, network and distance variables. The database encompasses more than 10 thousand funding rounds from 2002 to 2020. The precision of the gradient boosting technique was 24 percentage points higher than the one of a naive method. This predictive gain translates into savings or gains in capital allocation or investment promotion processes. We also evaluated feature importance and developed complementary models