Function approximation with learning networks in the financial field and its application to the interest rate sector

Quantitative analysis in the financial markets has traditionally been dominated by linear, parametric modeling approaches. Recent theoretical and empirical results suggest that nonlinear, nonparametric, multivariable regression techniques are more powerful tools to discover and capture nontrivial relationships between variables. In this work ways of improving models and thus forecasts are explored by adapting two different ways of specifying connectionist networks: radial basis function networks (RBF) and multilayer perceptrons (MLP). By employing these techniques we gain the potential to model complex data more effectively while at the same time we largely avoid imposing any particular and possibly incorrect model assumptions. Evolution strategy and a speeded up error backpropagation are utilized to estimate model parameters. To illustrate the application potential nonlinear models for Bund yields are estimated. For comparison benchmark models using a linear multivariable and a random walk approach are also estimated.