Hellinger distance to normal distribution as market invariant

Abstract

Main purpose of distance based portfolio constructions is in portfolio imitation. Here we construct portfolio based on Hellinger's distance from normal distribution. We empirically found that minimum of this distance drastically varies from market to market. Thus we suppose that it may be regarded as a form of market invariant, in a sense of helpful tool for market segmentation. We analyze its sensitivity. Though mean sensitivity was small it showed extreme sensitivity in some cases.