Strategic Markowitz Portfolio Optimization (SMPO): A Portfolio Return Booster

Abstract

In Financial Data Science and more specifically in Investment Analytics, Portfolio Optimization is a very crucial aspect. A portfolio consisting of a collection of securities, has certain weights assigned to each security. Banking on these weights, the overall Portfolio Return and Risk are determined. Investors always try to find the Optimized Portfolio by adjusting the weightage given to each security in the portfolio. In this paper, a diverse, practical and exemplar portfolio, also having tint of similarity among securities, is considered. It has stocks from 8 companies (not from or any particular market indices): General Motors (GM), Ford Motor Company (F), Cognizant (CTS), International Business Machines Corporation (IBM), Apple Technology Company (AAPL), Vivo (VIVO), Under Armour (UAA) and Nike (NKE). The Optimized Portfolio is constructed with adjusted weightage for each company in the portfolio using Strategic Markowitz Portfolio Optimization (SMPO). The obtained Optimized Portfolio yielded a Logarithmic Portfolio Return of 0.04268 at minimum Risk (Standard Deviation) of 0.14951 and maximum possible Logarithmic Return of 0.15873 at a Risk (Standard Deviation) of 0.17938. Using the Markowitz Portfolio Optimization in a strategic manner for such portfolio where there is diversity along with different shades of similarity, can fetch more Optimized Portfolio than obtained by the Classical approach of Markowitz Portfolio Optimization.