a genetic network programming model for pricing of basket default swaps (bds)

The credit derivatives market has experienced remarkable growth over the past decade. as such, there is a growing interest in tools for pricing of the most prominent credit derivative, the credit default swap (cds). in this paper, we propose a heuristic algorithm for pricing of basket default swaps (bds). for this purpose, genetic network programming (gnp), which is one of the recent evolutionary methods with graph structure as a subgroup of machine learning methods, is applied to assess basket default swap spreads. here gnp is an alternative way for modeling the default correlation structure among different reference entities in a basket default swap. in order to improve the efficiency of the proposed algorithm, gnp with vigorous connection (gn-pvc) is developed and used for the first time in this paper. to implement our model, we consider a basket consisting of 25 entities of the cdx.na.ig.5y index. we compare the heuristic results with the monte carlo ones and discuss the efficiency of the proposed algorithm. the impact of vigorous connection on the performance of gnp is also reported.