An Optimized Ensemble Learning Framework for Startup Success  Forecasting Utilizing Crunchbase Telemetry

P. Shailaja, S. Sandhya Rani

An Optimized Ensemble Learning Framework for Startup Success Forecasting Utilizing Crunchbase Telemetry

Authors

P. Shailaja, S. Sandhya Rani

Keywords:

Artificial Intelligence, Machine Learning, Predictive Analytics, Startup Success Forecasting, Crunchbase, Venture Capital Risk.

Abstract

Startups are primary engines of innovation and economic growth, yet they suffer from exceptionallyhigh early-stage failure rates. Traditional forecasting methodologies rely heavily on manual financialauditing, retrospective market analysis, and subjective evaluations of founding teams. These heuristic approaches are inherently unscalable, vulnerable to cognitive biases

References

McCarthy, Paul X., et al. "The Science of Startups: The Impact of Founder Personalities on Company Success." arXiv preprint arXiv:2302.07968 (2023).

Fuentes, Rolando, Dongmei Chen, and Frank A. Felder. "Systematically mapping innovations in electricity using startups: A comprehensive database analysis." Technology in Society (2023): 102282

Downloads

Published

2024-12-20

How to Cite

P. Shailaja, S. Sandhya Rani. (2024). An Optimized Ensemble Learning Framework for Startup Success Forecasting Utilizing Crunchbase Telemetry . Journal of Computational Analysis and Applications (JoCAAA), 33(08), 8949–8959. Retrieved from https://www.eudoxuspress.com/index.php/pub/article/view/5577