A Fused Large Language Model for Predicting Startup Success

TL;DR

This paper introduces a fused large language model that predicts startup success by analyzing textual descriptions and fundamental data, aiding investors in making informed decisions on VC platforms.

Contribution

The paper presents a novel fused large language model that combines textual and fundamental data to predict startup success, demonstrating its effectiveness on real-world VC platform data.

Findings

The fused model predicts startup success with significant accuracy.

Textual descriptions contribute substantially to predictive power.

The approach offers a practical decision support tool for investors.

Abstract

Investors are continuously seeking profitable investment opportunities in startups and, hence, for effective decision-making, need to predict a startup's probability of success. Nowadays, investors can use not only various fundamental information about a startup (e.g., the age of the startup, the number of founders, and the business sector) but also textual description of a startup's innovation and business model, which is widely available through online venture capital (VC) platforms such as Crunchbase. To support the decision-making of investors, we develop a machine learning approach with the aim of locating successful startups on VC platforms. Specifically, we develop, train, and evaluate a tailored, fused large language model to predict startup success. Thereby, we assess to what extent self-descriptions on VC platforms are predictive of startup success. Using 20,172 online profiles from Crunchbase, we find that our fused large language model can predict startup success, with textual self-descriptions being responsible for a significant part of the predictive power. Our work provides a decision support tool for investors to find profitable investment opportunities.