Skip to main content
eScholarship
Open Access Publications from the University of California

UCLA

UCLA Electronic Theses and Dissertations bannerUCLA

Kernel Density Estimation Clustering Algorithm with an Application in Characterizing Volatility Smiles

Abstract

An algorithm is devised for clustering observations based on the densities of points within each individual observations. The Kernel Density Estimation Clustering Algorithm (KCA) performs a search on the graph of the observations' group memberships, where group memberships determines the KDEs that in turn drive changes in the objective function. Option pricing theory is used to demonstrate the utility of the algorithm. Volatility smiles, 2- dimensional plots relating option strike prices and their implied volatilities, are the basis for grouping options.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View