Risk management using evolving possibilistic fuzzy modeling

Market risk exposure plays a key role for financial institutions risk management. A possible measure for this exposure is to evaluate losses likely to incur when the price of the portfolio’s assets declines using Value-at-Risk (VaR) estimates, one of the most prominent measure of financial downside market risk. This paper suggests an evolving possibilistic fuzzy modeling approach for VaR estimation. The approach is based on an extension of the possibilistic fuzzy c-means clustering and functional fuzzy rule-based modeling, which employs memberships and typicalities to update clusters and creates new clusters based on a statistical control distance-based criteria. ePFM also uses an utility measure to evaluate the quality of the current cluster structure. Computational experiments consider data of the main equity market index of Brazil, Ibovespa, from January 2000 to December 2012 for VaR estimation using ePFM, traditional econometric benchmarks such as GARCH and EWMA, and state of the art evolving approaches. The results show that ePFM is a potential candidate for VaR modeling, with better performance than alternative econometric approaches.