Intelligence in Finance — A Temporal Graph Neural Network platform for corporate stress prediction across the S&P 500.
GraphAlpha combines temporal graph architectures with LLM-powered analysis to detect early signals of corporate financial distress. The platform models 503 companies as an interconnected network, capturing supply-chain dependencies, shared investor relationships, and sector co-movements to predict risk propagation before traditional metrics react.
Interactive dashboard tracking 503 S&P 500 companies with risk scores, signal attribution, and a force-directed network graph with animated edge glow effects.
503-node interactive force-directed graph showing inter-company relationships across 5 edge types — supply chain, shared investors, sector co-membership, and more. Edges randomly glow to highlight active risk pathways.
Per-company analysis with risk gauge, signal category breakdown, temporal risk timeline, feature attribution charts, and 1-hop neighbor subgraph.
Auto-generated analyst notes and interactive chat powered by LLM, grounded in the model's signal attribution and graph context.
Benchmarking 5 architectures (MLP, Static GNN, TGN, TGAT, GraphAlpha Transformer) on AUROC, Sharpe ratio, hit rate, and cumulative PnL.
| Model | AUROC | AUPRC | Hit@20 | Sharpe |
|---|---|---|---|---|
| MLP Baseline | 0.700 | 0.450 | 50% | 1.20 |
| Static GNN | 0.736 | 0.520 | 58% | 1.65 |
| TGN | 0.710 | 0.500 | 55% | 1.40 |
| TGAT | 0.720 | 0.530 | 60% | 1.55 |
| GraphAlpha Transformer | 0.742 | 0.627 | 67% | 2.79 |
- Temporal Graph Neural Network with multi-head temporal attention over dynamic company graphs
- Multi-modal feature fusion: earnings call NLP drift, SEC filing language analysis, market microstructure signals
- LLM-augmented features: GPT-extracted sentiment, risk phrases, and management tone analysis from 10-K/10-Q filings and earnings transcripts
- Graph-based risk propagation: captures contagion effects through supply chain and investor networks
- Interactive AI analyst: conversational interface grounded in model explanations
- Frontend: React + TypeScript + Vite + Chart.js
- Backend: FastAPI + PyTorch
- Models: Custom Temporal Graph Transformer architecture
- LLM Integration: OpenAI GPT for analyst note generation and interactive chat
This software is under active development and is not recommended for production use. It is provided "as is", without warranty of any kind, express or implied.
- No investment advice. GraphAlpha does not provide investment recommendations, trading signals, or financial advice of any kind.
- No guarantee of accuracy. Risk scores, model outputs, and AI-generated analyst notes may contain errors and must not be relied upon for financial decisions.
- No liability. The authors and contributors accept no responsibility or liability for any financial loss, damage, or adverse outcome arising from the use of this software.
- Use at your own risk. By using this software, you acknowledge that it is under development and agree that the authors bear no obligation for its performance, availability, or suitability for any purpose.
This project is proprietary research. The frontend code is shared for demonstration purposes only. Model architectures, training pipelines, and data processing code are not included in this repository.