Publicação
Field Lab Yunoai: startup analytics - a machine learning approach to predict startup success based on founders´ features
| Resumo: | This thesis examines the impact of founders on startup success, focusing on education, professional experience, and LinkedIn metrics. It analyzes university and workplace prestige, including consultancy or VC experience, and LinkedIn follower count as a connectivity measure. Using advanced text analysis with SBERT and TF-IDF embeddings, it evaluates LinkedIn posts and profiles—a novel approach in predicting startup success. Founder personality traits are predicted through X platform data linked to LinkedIn profiles via Crunchbase. A three-layered success definition offers a comprehensive framework for evaluating outcomes, providing new insights into the relationship between founder characteristics and startup success. |
|---|---|
| Autores principais: | Schmidt, Benjamin |
| Assunto: | Startup success Funding metrics Failure prediction Founder-Market Fit (FMF) Machine learning Natural Language Processing (NLP) Startup dynamics |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | This thesis examines the impact of founders on startup success, focusing on education, professional experience, and LinkedIn metrics. It analyzes university and workplace prestige, including consultancy or VC experience, and LinkedIn follower count as a connectivity measure. Using advanced text analysis with SBERT and TF-IDF embeddings, it evaluates LinkedIn posts and profiles—a novel approach in predicting startup success. Founder personality traits are predicted through X platform data linked to LinkedIn profiles via Crunchbase. A three-layered success definition offers a comprehensive framework for evaluating outcomes, providing new insights into the relationship between founder characteristics and startup success. |
|---|