Pareto Driven Surrogate (ParDen-Sur) Assisted Optimisation of Multi-period Portfolio Backtest Simulations

TL;DR

This paper introduces ParDen-Sur, a surrogate-assisted framework that significantly accelerates hyper-parameter search in multi-period portfolio optimization, improving Pareto frontiers efficiently.

Contribution

The study presents ParDen-Sur, a novel surrogate modeling framework with reservoir sampling for look-ahead, enhancing hyper-parameter search in multi-period portfolio optimization.

Findings

ParDen-Sur speeds up hyper-parameter exploration by nearly 2x.

It achieves statistically significant improvements in Pareto frontiers.

Effective for both single- and multi-period portfolio optimization.

Abstract

Portfolio management is a multi-period multi-objective optimisation problem subject to a wide range of constraints. However, in practice, portfolio management is treated as a single-period problem partly due to the computationally burdensome hyper-parameter search procedure needed to construct a multi-period Pareto frontier. This study presents the \gls{ParDen-Sur} modelling framework to efficiently perform the required hyper-parameter search. \gls{ParDen-Sur} extends previous surrogate frameworks by including a reservoir sampling-based look-ahead mechanism for offspring generation in \glspl{EA} alongside the traditional acceptance sampling scheme. We evaluate this framework against, and in conjunction with, several seminal \gls{MO} \glspl{EA} on two datasets for both the single- and multi-period use cases. Our results show that \gls{ParDen-Sur} can speed up the exploration for optimal hyper-parameters by almost $2\times$ with a statistically significant improvement of the Pareto frontiers, across multiple \glspl{EA}, for both datasets and use cases.