Saved in:
Bibliographic Details
Main Authors: Cao, Yi, Chen, Zexun, Cong, Lin William, Shi, Heqing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.00987
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912995726065664
author Cao, Yi
Chen, Zexun
Cong, Lin William
Shi, Heqing
author_facet Cao, Yi
Chen, Zexun
Cong, Lin William
Shi, Heqing
contents We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable constraints within flexible neural function approximation. SKINNs jointly estimate neural network parameters and economically meaningful structural parameters in a single optimization problem, enforcing theoretical consistency not only on observed data but over a broader input domain through collocation, and therefore nesting approaches such as functional GMM, Bayesian updating, transfer learning, PINNs, and surrogate modeling. SKINNs define a class of M-estimators that are consistent and asymptotically normal with root-N convergence, sandwich covariance, and recovery of pseudo-true parameters under misspecification. We establish identification of structural parameters under joint flexibility, derive generalization and target-risk bounds under distributional shift in a convex proxy, and provide a restricted-optimal characterization of the weighting parameter that governs the bias-variance tradeoff. In an illustrative financial application to option pricing, SKINNs improve out-of-sample valuation and hedging performance, particularly at longer horizons and during high-volatility regimes, while recovering economically interpretable structural parameters with improved stability relative to conventional calibration. More broadly, SKINNs provide a general econometric framework for combining model-based reasoning with high-dimensional, data-driven estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00987
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
Cao, Yi
Chen, Zexun
Cong, Lin William
Shi, Heqing
Machine Learning
Artificial Intelligence
We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable constraints within flexible neural function approximation. SKINNs jointly estimate neural network parameters and economically meaningful structural parameters in a single optimization problem, enforcing theoretical consistency not only on observed data but over a broader input domain through collocation, and therefore nesting approaches such as functional GMM, Bayesian updating, transfer learning, PINNs, and surrogate modeling. SKINNs define a class of M-estimators that are consistent and asymptotically normal with root-N convergence, sandwich covariance, and recovery of pseudo-true parameters under misspecification. We establish identification of structural parameters under joint flexibility, derive generalization and target-risk bounds under distributional shift in a convex proxy, and provide a restricted-optimal characterization of the weighting parameter that governs the bias-variance tradeoff. In an illustrative financial application to option pricing, SKINNs improve out-of-sample valuation and hedging performance, particularly at longer horizons and during high-volatility regimes, while recovering economically interpretable structural parameters with improved stability relative to conventional calibration. More broadly, SKINNs provide a general econometric framework for combining model-based reasoning with high-dimensional, data-driven estimation.
title Bridging Structured Knowledge and Data: A Unified Framework with Finance Applications
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.00987