Investors are interested in predicting future success of startup companies, preferably using publicly available data which can be gathered using free online sources. Using public-only data has been shown to work, but there is still much room for improvement. Two of the best performing prediction experiments use 17 and 49 features respectively, mostly numeric and categorical in nature. In this paper, we significantly expand and diversify both the sources and the number of features (to 171) to achieve better prediction. Data collected from Crunchbase, the Google Search API, and Twitter (now X) are used to predict whether a company will raise a round of funding within a fixed time horizon. Much of the new features are textual and the Twitter subset include linguistic metrics such as measures of passive voice and parts-of-speech. A total of ten machine learning models are also evaluated for best performance. The adaptable model can be used to predict funding 1-5 years into the future, with a variable cutoff threshold to favor either precision or recall. Prediction with comparable assumptions generally achieves F scores above 0.730 which outperforms previous attempts in the literature (0.531), and does so with fewer examples. Furthermore, we find that the vast majority of the performance impact comes from the top 18 of 171 features which are mostly generic company observations, including the best performing individual feature which is the free-form text description of the company.
Using Deep Learning to Find the Next Unicorn: A Practical Synthesis
Motherbrain, EQT(Motherbrain,EQT集团);House of Innovation, Stockholm School of Economics(斯德哥尔摩经济学院创新中心);Stockholm University(斯德哥尔摩大学);Motherbrain AI Research, EQT Group(Motherbrain人工智能研究部,EQT集团)
CrunchLLM: Multitask LLMs for Structured Business Reasoning and Outcome Prediction
Department of Computer Science University of Kentucky(计算机科学系 俄亥俄大学);Department of Computer Science, Institute for Biomedical Informatics University of Kentucky(计算机科学系 生物医学信息学研究所 俄亥俄大学)
Rule Forest: Interpretable Ensembles of LLM-Generated Questions for Rare-Outcome Prediction
University of Oxford, United Kingdom Aarhus University, Aarhus, Denmark Centre de Recerca Matem\`atica, Barcelona, Spain Oliver Wyman, New York, United States Vela Research, San Francisco, United States