The Strategic Foresight of LLMs: Evidence from a Fully Prospective Venture Tournament
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910008497668096 |
|---|---|
| author | Csaszar, Felipe A. Peterson, Aticus Wilde, Daniel |
| author_facet | Csaszar, Felipe A. Peterson, Aticus Wilde, Daniel |
| contents | Can artificial intelligence outperform humans at strategic foresight -- the capacity to form accurate judgments about uncertain, high-stakes outcomes before they unfold? We address this question through a fully prospective prediction tournament using live Kickstarter crowdfunding projects. Thirty U.S.-based technology ventures, launched after the training cutoffs of all models studied, were evaluated while fundraising remained in progress and outcomes were unknown. A diverse suite of frontier and open-weight large language models (LLMs) completed 870 pairwise comparisons, producing complete rankings of predicted fundraising success. We benchmarked these forecasts against 346 experienced managers recruited via Prolific and three MBA-trained investors working under monitored conditions. The results are striking: human evaluators achieved rank correlations with actual outcomes between 0.04 and 0.45, while several frontier LLMs exceeded 0.60, with the best (Gemini 2.5 Pro) reaching 0.74 -- correctly ordering nearly four of every five venture pairs. These differences persist across multiple performance metrics and robustness checks. Neither wisdom-of-the-crowd ensembles nor human-AI hybrid teams outperformed the best standalone model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01684 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Strategic Foresight of LLMs: Evidence from a Fully Prospective Venture Tournament Csaszar, Felipe A. Peterson, Aticus Wilde, Daniel General Economics Economics Artificial Intelligence 68T50 (primary), 68T37 (secondary) I.2.7; H.4.2; J.4 Can artificial intelligence outperform humans at strategic foresight -- the capacity to form accurate judgments about uncertain, high-stakes outcomes before they unfold? We address this question through a fully prospective prediction tournament using live Kickstarter crowdfunding projects. Thirty U.S.-based technology ventures, launched after the training cutoffs of all models studied, were evaluated while fundraising remained in progress and outcomes were unknown. A diverse suite of frontier and open-weight large language models (LLMs) completed 870 pairwise comparisons, producing complete rankings of predicted fundraising success. We benchmarked these forecasts against 346 experienced managers recruited via Prolific and three MBA-trained investors working under monitored conditions. The results are striking: human evaluators achieved rank correlations with actual outcomes between 0.04 and 0.45, while several frontier LLMs exceeded 0.60, with the best (Gemini 2.5 Pro) reaching 0.74 -- correctly ordering nearly four of every five venture pairs. These differences persist across multiple performance metrics and robustness checks. Neither wisdom-of-the-crowd ensembles nor human-AI hybrid teams outperformed the best standalone model. |
| title | The Strategic Foresight of LLMs: Evidence from a Fully Prospective Venture Tournament |
| topic | General Economics Economics Artificial Intelligence 68T50 (primary), 68T37 (secondary) I.2.7; H.4.2; J.4 |
| url | https://arxiv.org/abs/2602.01684 |