The Fundamental Structure of Risk: From Characteristics to Covariance
Alexandre Alouadi, Charles-Albert Lehalle
Abstract
Estimating the covariance structure of financial assets typically relies on his- torical returns, making risk models dependent on noisy and asset-specific time se- ries. We propose the Characteristic-Driven Dynamic Factor Model (CD-DFM), a non-linear latent factor model that instead constructs a representation of the asset cross-section directly from observable firm characteristics, primarily company funda- mentals. The learned latent space jointly determines interpretable factor exposures and a forward covariance estimator, and is trained end to end on an objective that combines a Stein covariance loss with a factor reconstruction term, targeting the out-of-sample second moments used in risk management. Because the latent repre- sentation, i.e. the encoder depends only on characteristics, previously unseen assets can be embedded at inference time without retraining. Experiments on S&P 500 equities show that CD-DFM produces economically structured latent representa- tions, interpretable factor portfolios, and competitive covariance forecasts despite relying on substantially lower-frequency information than return-based approaches. Among the benchmarked methods, it is the only model that simultaneously combines characteristic-driven representations, factor interpretability, competitive covariance calibration, and zero-shot onboarding of unseen assets.
Read the AI summary and key takeaways for traders on WOBR Quant Research.