An LLM-generated set of yes/no founder questions, combined by simple threshold voting, is reported to predict startup success with 13.1% precision versus a 1.9% base rate, though the supporting evidence has significant gaps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data
An LLM-generated set of yes/no founder questions, combined by simple threshold voting, is reported to predict startup success with 13.1% precision versus a 1.9% base rate, though the supporting evidence has significant gaps.