An autoencoder factor model with a variational information-bottleneck penalty shows better out-of-sample asset pricing metrics at high factor counts, though the evidence lacks statistical rigor.
Perspectives on the future of asset pricing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
An Information Bottleneck Asset Pricing Model
An autoencoder factor model with a variational information-bottleneck penalty shows better out-of-sample asset pricing metrics at high factor counts, though the evidence lacks statistical rigor.