Abstract

Cross-sectional training of auto-encoder neural networks suggests that yield-curve dynamics are well described by two to three factors and are dynamically arbitrage-free. In this article, we discuss the evidence and identify stochastic model parameters that support the auto-encoders.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call