Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Career Data Runs Out: Structured Feature Engineering and Signal Limits for Founder Success Prediction
Yagiz Ihlamur
Predicting startup success from founder career data is hard. The signal is weak, the labels are rare (9%), and most founders who succeed look almost identical to those who fail. We…
cs.LG2026
From Stochastic Answers to Verifiable Reasoning: Interpretable Decision-Making with LLM-Generated Code
Anirudh Jaidev Mahesh, Ben Griffin, Fuat Alican +8
Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility…