Calibrating the Dynamic Nelson-Siegel Model: A Practitioner Approach

The dynamic version of the Nelson-Siegel model has shown useful applications in the investment management industry. These applications go from forecasting the yield curve to portfolio risk management. Because of the complexity in the estimation of the parameters, some practitioners are unable to benefit from the uses of this model. In this note we present two approximations to estimate the time series of the model's factors. The first one has a more technical aim, focusing on the construction of a representative base to work, and uses a genetic algorithm to face the optimization problem. The second approximation has a practitioner spirit, focusing on the easiness of implementation. The results show that both approximations have good fitting for the U.S. Treasury bonds market.