From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908528710516736 |
|---|---|
| author | Kumar, Mihir Yin, Aaron Ontoyin Salifu, Zakari Amoaba, Kelvin Samuel, Afriyie Kwesi Alican, Fuat Ihlamur, Yigit |
| author_facet | Kumar, Mihir Yin, Aaron Ontoyin Salifu, Zakari Amoaba, Kelvin Samuel, Afriyie Kwesi Alican, Fuat Ihlamur, Yigit |
| contents | This paper presents a framework for predicting rare, high-impact outcomes by integrating large language models (LLMs) with a multi-model machine learning (ML) architecture. The approach combines the predictive strength of black-box models with the interpretability required for reliable decision-making. We use LLM-powered feature engineering to extract and synthesize complex signals from unstructured data, which are then processed within a layered ensemble of models including XGBoost, Random Forest, and Linear Regression. The ensemble first produces a continuous estimate of success likelihood, which is then thresholded to produce a binary rare-event prediction. We apply this framework to the domain of Venture Capital (VC), where investors must evaluate startups with limited and noisy early-stage data. The empirical results show strong performance: the model achieves precision between 9.8X and 11.1X the random classifier baseline in three independent test subsets. Feature sensitivity analysis further reveals interpretable success drivers: the startup's category list accounts for 15.6% of predictive influence, followed by the number of founders, while education level and domain expertise contribute smaller yet consistent effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_08140 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital Kumar, Mihir Yin, Aaron Ontoyin Salifu, Zakari Amoaba, Kelvin Samuel, Afriyie Kwesi Alican, Fuat Ihlamur, Yigit Machine Learning Artificial Intelligence This paper presents a framework for predicting rare, high-impact outcomes by integrating large language models (LLMs) with a multi-model machine learning (ML) architecture. The approach combines the predictive strength of black-box models with the interpretability required for reliable decision-making. We use LLM-powered feature engineering to extract and synthesize complex signals from unstructured data, which are then processed within a layered ensemble of models including XGBoost, Random Forest, and Linear Regression. The ensemble first produces a continuous estimate of success likelihood, which is then thresholded to produce a binary rare-event prediction. We apply this framework to the domain of Venture Capital (VC), where investors must evaluate startups with limited and noisy early-stage data. The empirical results show strong performance: the model achieves precision between 9.8X and 11.1X the random classifier baseline in three independent test subsets. Feature sensitivity analysis further reveals interpretable success drivers: the startup's category list accounts for 15.6% of predictive influence, followed by the number of founders, while education level and domain expertise contribute smaller yet consistent effects. |
| title | From Limited Data to Rare-event Prediction: LLM-powered Feature Engineering and Multi-model Learning in Venture Capital |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2509.08140 |