Multimodal conflict-aware and generative-enhanced AI for early-stage startup risk prediction

Early-stage startups are central to innovation-driven economies, yet their failure rates remain persistently high, with more than half of new ventures not surviving their first three to five years. Accurately assessing the risk of young ventures is challenging because relevant signals are dispersed across heterogeneous sources, including entrepreneurial narratives, early financial indicators, and founders’ positions in entrepreneurial networks. Most existing models either focus on a single modality or treat multimodal features as independent inputs, overlooking whether cross-source discrepancies contain additional information and struggling with small, imbalanced datasets. This paper proposes a conflict-aware, generative-enhanced multimodal framework for predicting startup risk within 36 months after the initial institutional evaluation. The model jointly encodes business plan and interview text, structured financial features, and founder-centric social network information via transformer, multilayer perceptron, and heterogeneous graph neural network encoders. Cross-modal contrastive learning aligns the three modalities into a shared representation space, while a modal conflict attention module computes representation-level discrepancies between textual, financial, and network signals as candidate features for further inspection. To mitigate data scarcity and class imbalance, we further introduce a conditional GAN operating in the fused latent space to generate label- and conflict-conditioned synthetic representations that expose the classifier to both typical and strategically conflictual patterns. Experiments on a real-world dataset of 4,500 early-stage startups show that the proposed framework outperforms structured, text-feature, network-feature, and multimodal baselines. Compared to the best multimodal fusion baseline, our model improves AUROC from 0.82 to 0.87 and AUPRC from 0.53 to 0.62, with consistent gains in positive-class F \(_1\) and balanced accuracy. Ablation studies confirm the incremental contributions of contrastive alignment, modal conflict attention, and generative augmentation. A held-out construct-validity analysis further shows that the learned conflict representation tracks independently derived cross-domain discrepancy measures, while its non-monotonic outcome gradient supports using it as an inspection signal rather than a stand-alone diagnostic.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-18
DOI
https://doi.org/10.1038/s41598-026-80661-4
Citations
2
Primary Topic
Private Equity and Venture Capital
Type
article
Field-Weighted Citation Impact
5.13
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Multimodal conflict-aware and generative-enhanced AI for early-stage startup risk prediction

Jiaying Xi
2 citations
Scientific Reports
Private Equity and Venture Capital
5.13
article

Multimodal conflict-aware and generative-enhanced AI for early-stage startup risk prediction

Jiaying Xi
article en
2 citations

Abstract

Early-stage startups are central to innovation-driven economies, yet their failure rates remain persistently high, with more than half of new ventures not surviving their first three to five years. Accurately assessing the risk of young ventures is challenging because relevant signals are dispersed across heterogeneous sources, including entrepreneurial narratives, early financial indicators, and founders’ positions in entrepreneurial networks. Most existing models either focus on a single modality or treat multimodal features as independent inputs, overlooking whether cross-source discrepancies contain additional information and struggling with small, imbalanced datasets. This paper proposes a conflict-aware, generative-enhanced multimodal framework for predicting startup risk within 36 months after the initial institutional evaluation. The model jointly encodes business plan and interview text, structured financial features, and founder-centric social network information via transformer, multilayer perceptron, and heterogeneous graph neural network encoders. Cross-modal contrastive learning aligns the three modalities into a shared representation space, while a modal conflict attention module computes representation-level discrepancies between textual, financial, and network signals as candidate features for further inspection. To mitigate data scarcity and class imbalance, we further introduce a conditional GAN operating in the fused latent space to generate label- and conflict-conditioned synthetic representations that expose the classifier to both typical and strategically conflictual patterns. Experiments on a real-world dataset of 4,500 early-stage startups show that the proposed framework outperforms structured, text-feature, network-feature, and multimodal baselines. Compared to the best multimodal fusion baseline, our model improves AUROC from 0.82 to 0.87 and AUPRC from 0.53 to 0.62, with consistent gains in positive-class F \(_1\) and balanced accuracy. Ablation studies confirm the incremental contributions of contrastive alignment, modal conflict attention, and generative augmentation. A held-out construct-validity analysis further shows that the learned conflict representation tracks independently derived cross-domain discrepancy measures, while its non-monotonic outcome gradient supports using it as an inspection signal rather than a stand-alone diagnostic.

Scientific Reports
Zhejiang Technical Institute of Economics (CN)
Openalex Percentile: Top 7%
Private Equity and Venture Capital
5.13
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon