Teaching Economics to the Machines

Structural economic models, while parsimonious and interpretable, often exhibit poor data fit and limited forecasting performance. Machine learning models, by contrast, offer substantial flexibility but are prone to overfitting and weak out-of-distribution generalization. We propose a theory-guided transfer learning framework that integrates structural restrictions from economic theory into machine learning models. The approach pre-trains a neural network on synthetic data generated by a structural model and then fine-tunes it using empirical data, allowing potentially misspecified economic restrictions to inform and regularize learning on empirical data. Applied to option pricing, our model substantially outperforms both structural and purely data-driven benchmarks, with especially large gains in small samples, under unstable market conditions, and when model misspecification is limited. Beyond performance, the framework provides diagnostics for improving structural models and introduces a new model-comparison metric based on data-model complementarity.