Consistent Recalibration Models and Deep Calibration
This addresses a computational bottleneck in financial modeling for derivatives pricing, though it appears incremental as it builds on existing CRC models.
The authors tackled the problem of numerical intractability in Consistent Recalibration models for dynamic term structures of derivatives' prices, and overcame it by using machine learning techniques to store drift term information in neural networks, enabling efficient simulation for the first time.
Consistent Recalibration models (CRC) have been introduced to capture in necessary generality the dynamic features of term structures of derivatives' prices. Several approaches have been suggested to tackle this problem, but all of them, including CRC models, suffered from numerical intractabilities mainly due to the presence of complicated drift terms or consistency conditions. We overcome this problem by machine learning techniques, which allow to store the crucial drift term's information in neural network type functions. This yields first time dynamic term structure models which can be efficiently simulated.