• Working Paper
    • EN
Share
Working-paper.jpg
2.10.2019 30

Machine Learning Optimization Algorithms & Portfolio Allocation

Published October 2, 2019

> 10 minutes

> 10 minutes

ABSTRACT


Portfolio optimization emerged with the seminal paper of Markowitz (1952). The original mean-variance framework is appealing because it is very efficient from a computational point of view. However, it also has one well-established failing since it can lead to portfolios that are not optimal from a financial point of view (Michaud, 1989). Nevertheless, very few models have succeeded in providing a real alternative solution to the Markowitz model. The main reason lies in the fact that most academic portfolio optimization models are intractable in real life although they present solid theoretical properties. By intractable we mean that they can be implemented for an investment universe with a small number of assets using a lot of computational resources and skills, but they are unable to manage a universe with dozens or hundreds of assets. However, the emergence and the rapid development of robo-advisors means that we need to rethink portfolio optimization and go beyond the traditional mean-variance optimization approach.

Another industry and branch of science has faced similar issues concerning large-scale optimization problems. Machine learning and applied statistics have long been associated with linear and logistic regression models. Again, the reason was the inability of optimization algorithms to solve high-dimensional industrial problems. Nevertheless, the end of the 1990s marked an important turning point with the development and the rediscovery of several methods that have since produced impressive results. The goal of this paper is to show how portfolio allocation can benefit from the development of these largescale optimization algorithms. Not all of these algorithms are useful in our case, but four of them are essential when solving complex portfolio optimization problems. These four algorithms are the coordinate descent, the alternating direction method of multipliers, the proximal gradient method and the Dykstra’s algorithm. This paper reviews them and shows how they can be implemented in portfolio allocation.

To find out more, download the full paper


This website is solely for informational purposes.
 
This website does not constitute an offer to sell, a solicitation of an offer to buy, or a recommendation of any security or any other product or service. Any securities, products, or services referenced may not be registered for sale with the relevant authority in your jurisdiction and may not be regulated or supervised by any governmental or similar authority in your jurisdiction.
 
Furthermore, nothing in this website is intended to provide tax, legal, or investment advice and nothing in this website should be construed as a recommendation to buy, sell, or hold any investment or security or to engage in any investment strategy or transaction. There is no guarantee that any targeted performance or forecast will be achieved.

Get in touch with us

Our online help service is available to answer your question

My personal information

If you have a question about our company or one of our products, please complete the form to get in touch. Please do not mention your account numbers or critical data in this form.

Civility*

(*) Required fields
All our job offers (Permanent and temporary position, Internship, Apprenticeship or VIE) are available on our dedicated website: https://jobs.amundi.com.

Register and apply directly online.

Amundi on Twitter