Conditional Portfolio Optimization: Using Machine Learning to Adapt Capital Allocations to Market Regimes

18 Pages Posted: 11 Apr 2023 Last revised: 26 Jul 2023

See all articles by Ernest Chan

Ernest Chan

PredictNow.ai

Haoyu Fan

PredictNow.ai

Sudarshan Sawal

PredictNow.ai

Quentin Viville

PredictNow.ai

Date Written: June 28, 2023

Abstract

Conditional Portfolio Optimization is a portfolio optimization technique that adapts to market regimes via machine learning. Traditional portfolio optimization methods take summary statistics of historical constituent returns as input and produce a portfolio that was optimal in the past, but may not be optimal going forward. Machine learning can condition the optimization on a large number of market features and propose a portfolio that is optimal under the current market regime. We call this Conditional Portfolio Optimization (CPO). Applications on portfolios in vastly different markets suggest that CPO can outperform traditional optimization methods under varying market regimes.

Keywords: portfolio optimization, machine learning, factor models

JEL Classification: G11, G17

Suggested Citation

Chan, Ernest and Fan, Haoyu and Sawal, Sudarshan and Viville, Quentin, Conditional Portfolio Optimization: Using Machine Learning to Adapt Capital Allocations to Market Regimes (June 28, 2023). Available at SSRN: https://ssrn.com/abstract=4383184 or http://dx.doi.org/10.2139/ssrn.4383184

Ernest Chan (Contact Author)

PredictNow.ai ( email )

56 Niagara on the Green Blvd
Niagara-on-the-Lake, L0S 1J0
Canada

Haoyu Fan

PredictNow.ai ( email )

56 Niagara on the Green Blvd
Niagara-on-the-Lake, L0S 1J0
Canada

Sudarshan Sawal

PredictNow.ai ( email )

Quentin Viville

PredictNow.ai ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
4,253
Abstract Views
8,889
Rank
5,207
PlumX Metrics