3 papers
q-fin.ST2026
Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations
Marcus Gawronsky, Chun-Sung Huang
Portfolio risk assessment ordinarily relies on reliable estimates of cross-asset return covariances, which are difficult to obtain in short, high-dimensional panels. We show that f…
q-fin.ST2026
Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
Marcus Gawronsky, Chun-Sung Huang
Spatial return models take the interaction matrix as given and leave feedback uninterpreted. We construct a bandwidth-free field from firms' language-model article embedding distri…
q-fin.CP2024
Systematic Covariance Envelopes from Wasserstein Geometry: Evidence from Language-Model Representations
Marcus Gawronsky, Chun-Sung Huang
Firm characteristics are commonly represented as fixed vectors, even though evidence about firms' operations arrives as heterogeneous collections of articles reports. We study how…