Yield Curve Fitting with Artificial Intelligence: A Comparison of Standard Fitting Methods with AI Algorithms

Abstract

The yield curve is one of the fundamental input parameters of pricing theories in capital markets. Information about yields can be observed in a discrete form either directly through traded yield instruments (e.g. Interest Rate SWAP's) or indirectly through prices of bonds (e.g. Government Bonds). Capital markets usually create benchmark yield curves for specific and very liquid market instruments or issuers where many different quotes of individual yield information for specific maturities are observable. The standard methods to construct a continuous yield curve from the discrete observable yield data quotes are either a fit of a mathematical model function or a splines interpolation. This article expands the standard methods to Artificial Intelligence algorithms, which have the advantage to avoid any assumptions for the mathematical model functions of the yield curve and can conceptually adapt easily to any market changes. Nowadays the most widely used "risk free" yield curve in capital markets is the OIS curve, which is derived from observable Overnight Index SWAP's and is used in this article as the benchmark curve to derive and compare the different yield curve fits.

Keywords: Artificial Intelligence, Yield Curve, Fitting, Splines, Nelson-Siegel-Svensson Model, OIS

JEL Classification: C14, C45, C52, C67, E43