Delta Hedging with Transaction Costs: Dynamic Multiscale Strategy using Neural Nets

TL;DR

This paper introduces a neural network-based dynamic multiscale hedging strategy that optimizes transaction timing under costs and risk constraints, improving risk management in financial portfolios.

Contribution

It proposes a novel neural network approach to determine optimal hedging frequencies dynamically, incorporating transaction costs and partial information.

Findings

Neural network effectively predicts optimal hedging periods.

Strategy outperforms fixed-frequency hedging in simulations.

Adaptive approach reduces transaction costs while maintaining risk control.

Abstract

In most real scenarios the construction of a risk-neutral portfolio must be performed in discrete time and with transaction costs. Two human imposed constraints are the risk-aversion and the profit maximization, which together define a nonlinear optimization problem with a model-dependent solution. In this context, an optimal fixed frequency hedging strategy can be determined a posteriori by maximizing a sharpe ratio simil path dependent reward function. Sampling from Heston processes, a convolutional neural network was trained to infer which period is optimal using partial information, thus leading to a dynamic hedging strategy in which the portfolio is hedged at various frequencies, each weighted by the probability estimate of that frequency being optimal.