A machine learning efficient frontier

Brian Clark; Zachary Feinstein; Majeed Simaan

doi:10.1016/j.orl.2020.07.016

A machine learning efficient frontier

School of Business

Rensselaer Polytechnic Institute

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

We propose a simple approach to bridge between portfolio theory and machine learning. The outcome is an out-of-sample machine learning efficient frontier based on two assets, high risk and low risk. By rotating between the two assets, we show that the proposed frontier dominates the mean–variance efficient frontier out-of-sample. Our results, therefore, shed important light on the appeal of machine learning into portfolio selection under estimation risk.

Original language	English
Pages (from-to)	630-634
Number of pages	5
Journal	Operations Research Letters
Volume	48
Issue number	5
DOIs	https://doi.org/10.1016/j.orl.2020.07.016
State	Published - Sep 2020

Keywords

Estimation risk
Machine learning
Portfolio theory
Tactical asset allocation

Access to Document

10.1016/j.orl.2020.07.016

Cite this

@article{daef24744d924c16b3d8d17a9682c8f5,

title = "A machine learning efficient frontier",

abstract = "We propose a simple approach to bridge between portfolio theory and machine learning. The outcome is an out-of-sample machine learning efficient frontier based on two assets, high risk and low risk. By rotating between the two assets, we show that the proposed frontier dominates the mean–variance efficient frontier out-of-sample. Our results, therefore, shed important light on the appeal of machine learning into portfolio selection under estimation risk.",

keywords = "Estimation risk, Machine learning, Portfolio theory, Tactical asset allocation",

author = "Brian Clark and Zachary Feinstein and Majeed Simaan",

note = "Publisher Copyright: {\textcopyright} 2020 Elsevier B.V.",

year = "2020",

month = sep,

doi = "10.1016/j.orl.2020.07.016",

language = "English",

volume = "48",

pages = "630--634",

number = "5",

}

TY - JOUR

T1 - A machine learning efficient frontier

AU - Clark, Brian

AU - Feinstein, Zachary

AU - Simaan, Majeed

PY - 2020/9

Y1 - 2020/9

N2 - We propose a simple approach to bridge between portfolio theory and machine learning. The outcome is an out-of-sample machine learning efficient frontier based on two assets, high risk and low risk. By rotating between the two assets, we show that the proposed frontier dominates the mean–variance efficient frontier out-of-sample. Our results, therefore, shed important light on the appeal of machine learning into portfolio selection under estimation risk.

AB - We propose a simple approach to bridge between portfolio theory and machine learning. The outcome is an out-of-sample machine learning efficient frontier based on two assets, high risk and low risk. By rotating between the two assets, we show that the proposed frontier dominates the mean–variance efficient frontier out-of-sample. Our results, therefore, shed important light on the appeal of machine learning into portfolio selection under estimation risk.

KW - Estimation risk

KW - Machine learning

KW - Portfolio theory

KW - Tactical asset allocation

UR - https://www.scopus.com/pages/publications/85089197941

UR - https://www.scopus.com/pages/publications/85089197941#tab=citedBy

U2 - 10.1016/j.orl.2020.07.016

DO - 10.1016/j.orl.2020.07.016

M3 - Article

AN - SCOPUS:85089197941

SN - 0167-6377

VL - 48

SP - 630

EP - 634

JO - Operations Research Letters

JF - Operations Research Letters

IS - 5

ER -

A machine learning efficient frontier

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this