Naslov
Neural networks and vector autoregressive model in forecasting yield curve

Autori
Aljinović, Zdravka ; Poklepović, Tea

Izvornik
International Conference on Information Technology (Amman) (2306-6105) 1 (2013); 1-8

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
yield curve; Nelson-Siegel model; Neural network; Vector autoregressive model

Sažetak
Yield curve represents a relationship between the rate of return and maturity of certain securities. A range of activities on the market is determined by the abovementioned relationship ; therefore its significance is unquestionable. Besides that, its shape reflects the shape of the economy, i.e. it can predict recession. These are the reasons why it is very important to properly and accurately estimate the yield curve. There are various models evolved for its estimation ; however the most used is a parametric Nelson-Siegel model. What is also important is the ability of forecasting yield curve. Therefore in this paper after the estimation of weekly yield curves on Croatian financial market in years 2011 and 2012 with Nelson-Siegel model, yield curves are predicted using Neural networks and Vector autoregressive model. The obtained results are compared and conclusions regarding forecasting yield curves are given.

Izvorni jezik
Engleski

Znanstvena područja
Ekonomija

POVEZANOST RADA