Torben Antretter

TL;DR: A comprehensive review of the literature on new venture survival can be found in this article, where the authors provide an evaluative overview of the existing literature and highlight important methodological aspects in this research field.

TL;DR: This study shows that online legitimacy as a measure of social appreciation based on Twitter content can be used to accurately predict new venture survival and provides an account of how to use machine learning methodologies in entrepreneurship research.

TL;DR: Investors increasingly use machine learning algorithms to support their early stage investment decisions, but it remains unclear if algorithms can make better investment decisions and if they can be trusted.

TL;DR: In this article, the authors investigate the performance effects of business angel portfolio industry diversification and find a nonlinear (S-shaped) relationship between portfolio industry diversity and performance, and pay specific attention to a proposed overdiversification effect that takes place at high levels of portfolio industry divergence and show that individuals' access to industry knowledge through their co-investment networks.

TL;DR: This study will provide an evidence-based taxonomy of digital traces for predicting early stage startup survival, identify the most importantdigital traces for doing so and benchmark the predictive approach against the actual investments of 339 business angels.