A1015
Title: Consistent recalibration models and deep calibration
Authors: Matteo Gambara - ETHZ (Switzerland) [presenting]
Josef Teichmann - ETHZ (Switzerland)
Abstract: 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 of consistency conditions. We overcome this problem by machine learning techniques, which allow storing the crucial drift term's information in neural network type functions. This yields first-time dynamic term structure models which can be efficiently simulated. As a side result, we are able to simulate for an indefinite time the evolution of an implied volatility surface under no-arbitrage constraints.
