A Comparision of Three Network Portfolio Selection Methods -- Evidence from the Dow Jones

TL;DR

This study compares three network-based portfolio selection methods with random and industry-based approaches using Dow Jones data from 2001 to 2013, finding similar performance across methods for small private investors.

Contribution

It provides an empirical comparison of network methods against traditional selection strategies over a long-term period.

Findings

Network methods perform comparably to random selection.

No significant advantage of network methods over industry-based or random approaches.

Results are specific to small private investor portfolios.

Abstract

We compare three network portfolio selection methods; hierarchical clustering trees, minimum spanning trees and neighbor-Nets, with random and industry group selection methods on twelve years of data from the 30 Dow Jones Industrial Average stocks from 2001 to 2013 for very small private investor sized portfolios. We find that the three network methods perform on par with randomly selected portfolios.