Model Calibration with Neural Networks

This article focuses on the effective calibration of a quantitative model to a specific data set using a novel method in the form of machine learning. It provides an alternative calibration method using artificial neural networks which reduces the time constraint imposed on a model. These neural networks allow for a training process to be run separately, significantly speeding up the calibration period.

The number of layers and neurons per layer are variable and must be determined. Once found, the calibration will be done by a supervised learning phase which is done offline and is followed by the evaluation phase. By offloading the work involved in calibrating a model by using a neural network, the time to calibrate the model is much more efficient and speedy, as opposed to the hours or days live calibrations require.

By reading this paper one will understand the procedure for calibrating a quantitative model to a certain data set and an example of the calibration of a simple Hull-White model. It should be noted in this test the trained model performs well for a limited period of time, suggesting regularly re-calibrating to refreshed data is necessary. Read the full paper by Andres Hernandez here.

Start Algo Trading Today!

Get your free token to connect to the REST API and start trading. To generate your token:

  1. Register for a free practice account here.
  2. Log into and click on the account ID in the upper right corner.
  3. Click token management and generate your token.

Risk Warning: The FXCM Group does not guarantee accuracy and will not accept liability for any loss or damage which arise directly or indirectly from use of or reliance on information contained within the webinars. The FXCM Group may provide general commentary which is not intended as investment advice and must not be construed as such. FX/CFD trading carries a risk of losses in excess of your deposited funds and may not be suitable for all investors. Please ensure that you fully understand the risks involved.