Estimation of the yield curve for Costa Rica using combinatorial optimization metaheuristics applied to nonlinear regression

TL;DR

This paper compares four combinatorial optimization metaheuristics to improve the estimation of Costa Rica's yield curve using nonlinear regression models, achieving better results than classical methods.

Contribution

It introduces the application of four metaheuristics to optimize yield curve estimation, enhancing accuracy over traditional quasi-Newton methods.

Findings

Particle swarm optimization and simulated annealing yielded the best results.

Metaheuristics improved the estimation accuracy of the yield curve.

Classical methods often got trapped in local minima.

Abstract

The term structure of interest rates or yield curve is a function relating the interest rate with its own term. Nonlinear regression models of Nelson-Siegel and Svensson were used to estimate the yield curve using a sample of historical data supplied by the National Stock Exchange of Costa Rica. The optimization problem involved in the estimation process of model parameters is addressed by the use of four well known combinatorial optimization metaheuristics: Ant colony optimization, Genetic algorithm, Particle swarm optimization and Simulated annealing. The aim of the study is to improve the local minima obtained by a classical quasi-Newton optimization method using a descent direction. Good results with at least two metaheuristics are achieved, Particle swarm optimization and Simulated annealing. Keywords: Yield curve, nonlinear regression, Nelson-