Online Program Home
My Program

Abstract Details

Activity Number: 433
Type: Contributed
Date/Time: Tuesday, August 2, 2016 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #320379 View Presentation
Title: Risk, Value, and Popularity: A Network-Based Approach to Stock Portfolio Diversification
Author(s): Natallia Katenka* and Gregory Breard
Companies: University of Rhode Island and University of Rhode Island
Keywords: Networks ; Partial Correlation ; Canonical Correlation ; Risk Management ; Stock Market

Portfolio diversification is a core principle of any sound investment strategy, the purpose being to minimize risk while maximizing returns. To construct a diverse portfolio, one must understand the interrelations between the industrial sectors that they comprise. Ideally, these relationships would be inferred without any preconceptions about the existence, or lack thereof, a connection between companies. This would allow decisions to be based on the underlying structure of the market rather than on assumptions. Furthermore, a measure that discounts the influence of other companies is desirable. Partial correlation applied to stock price data has been one method used that meets these criteria, though is limited to a single attribute.To factors multiple attributes, we propose to use the partial canonical correlations (PCC) between the value profiles (price), popularity profiles (volume), and risk profiles (volatility) for pairings of stocks as a superior strategy. We induce a partial canonical correlation network (PCCN) using one year of data for a small group of companies and select portfolios based on the structure of the network. PCCN approach results in more diverse portfolios.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association