Inflexible Multi-Asset Hedging of incomplete market

TL;DR

This paper develops a new jump-diffusion model and compares neural network architectures to hedge assets effectively in incomplete markets with multiple sources of market imperfections.

Contribution

It introduces a novel jump-diffusion model for asset prices and evaluates three neural network architectures for hedging in incomplete markets.

Findings

Mogrifier-LSTM achieves the fastest training times.

Mogrifier-LSTM provides the best hedging performance under MSE and Huber Loss.

Neural network-based hedging strategies outperform traditional methods in incomplete markets.

Abstract

Models trained under assumptions in the complete market usually don't take effect in the incomplete market. This paper solves the hedging problem in incomplete market with three sources of incompleteness: risk factor, illiquidity, and discrete transaction dates. A new jump-diffusion model is proposed to describe stochastic asset prices. Three neutral networks, including RNN, LSTM, Mogrifier-LSTM are used to attain hedging strategies with MSE Loss and Huber Loss implemented and compared.As a result, Mogrifier-LSTM is the fastest model with the best results under MSE and Huber Loss.