Conditional autoencoder pricing model for energy commodities

We propose a conditional latent factor asset pricing model for energy commodities (CAE) that uses a modified conditional autoencoder neural network to capture the non-linear relationship between latent factors and factor loadings. In addition to spot prices, we incorporate 127 macroeconomic and 598 energy information characteristics to extract the factor loadings. The empirical results demonstrate the high-quality performance of the model in out-of-sample testing. Furthermore, by analyzing characteristic importance, we find that energy information characteristics, particularly coal, electricity, and crude oil and natural gas resource development, play a dominant role in explaining the excess returns of energy commodities.