ExeAnalyzer: A Deep Generative Adversarial Network for Multimodal Online Impression Analysis and Startup Funding Prediction

Abstract

With the rise of equity crowdfunding platforms, entrepreneurs' online impressions are of great importance to startups' initial funding success. Guided by the design science research methodology, one contribution of our research is to design a novel Generative Adversarial Network, namely ExeAnalyzer, to analyze CEOs' online impressions by using multimodal data collected from social media platforms. More specifically, ExeAnalyzer can detect CEOs' first impressions, personalities, and other sociometric attributes. Based on a dataset of 7,806 startups extracted from AngelList, another contribution of our research is the empirical analysis of the relationship between CEOs' online impressions and startups' funding successes. Our empirical analysis shows that CEOs' impression of dominance is negatively related to startups' funding performance, while the social desirability of CEOs is positively associated with startups' funding success. Our empirical study also confirms that the impression features extracted by ExeAnalyzer have significant predictive power on startups' funding performance.