Neighbouring Assets

Abstract

Firms with similar characteristics display similar expected returns. Defining neighboring assets as those with the most similar set of characteristics, I show that past returns of an asset's neighbors predict its future returns. If a majority of an asset's neighbors have performed poorly (well) in the past, it is likely that this asset also performs poorly (well) in the future. By classifying each asset into a decile portfolio based on the past performance of its neighbors, with 94 characteristics, a long-short portfolio generates an out-of-sample annualized Sharpe ratio of 1.40 with a monthly alpha of 1.75% (t = 9.45).

Keywords: Asset pricing, portfolios, cross-section of expected returns, stock characteristics, machine learning

JEL Classification: G10, G11, G14, C14, C11, C21, C22, C23, C58