CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market
By: Dixon Domfeh, Saeid Safarveisi
Potential Business Impact:
Predicts insurance prices by studying money connections.
Traditional models for pricing catastrophe (CAT) bonds struggle to capture the complex, relational data inherent in these instruments. This paper introduces CATNet, a novel framework that applies a geometric deep learning architecture, the Relational Graph Convolutional Network (R-GCN), to model the CAT bond primary market as a graph, leveraging its underlying network structure for spread prediction. Our analysis reveals that the CAT bond market exhibits the characteristics of a scale-free network, a structure dominated by a few highly connected and influential hubs. CATNet demonstrates high predictive performance, significantly outperforming a strong Random Forest benchmark. The inclusion of topological centrality measures as features provides a further, significant boost in accuracy. Interpretability analysis confirms that these network features are not mere statistical artifacts; they are quantitative proxies for long-held industry intuition regarding issuer reputation, underwriter influence, and peril concentration. This research provides evidence that network connectivity is a key determinant of price, offering a new paradigm for risk assessment and proving that graph-based models can deliver both state-of-the-art accuracy and deeper, quantifiable market insights.
Similar Papers
Deep learning CAT bond valuation
Pricing of Securities
Computers learn to guess how much insurance costs.
Unveiling Nonlinear Dynamics in Catastrophe Bond Pricing: A Machine Learning Perspective
Computational Finance
Prices risky insurance bonds more accurately.
Crime Hotspot Prediction Using Deep Graph Convolutional Networks
Machine Learning (CS)
Finds crime hotspots to keep cities safer.