Hybrid Photonic Quantum Reservoir Computing for High-Dimensional Financial Surface Prediction

TL;DR

This paper introduces a hybrid photonic quantum reservoir computing framework for high-dimensional financial surface prediction, demonstrating superior accuracy and efficiency over classical methods with zero trainable quantum parameters.

Contribution

It presents a novel hybrid quantum-classical pipeline with fixed quantum feature extractors and classical regression, achieving high accuracy in financial surface prediction.

Findings

Achieves lowest surface RMSE of 0.0425 with sub-millisecond inference.

Fixed quantum feature extractors outperform variational quantum methods in low-data scenarios.

Quantum layer has zero trainable parameters, avoiding barren plateaus.

Abstract

We propose a hybrid photonic quantum reservoir computing (QRC) framework for swaption surface prediction. The pipeline compresses 224-dimensional surfaces to a 20-dimensional latent space via a sparse denoising autoencoder, extracts 1,215 Fock-basis features from an ensemble of three fixed photonic reservoirs, concatenates them with a 120-dimensional classical context, and maps the resulting 1,335-dimensional feature vector to predictions with Ridge regression. We benchmark against 10 classical and quantum baselines on six held-out trading days. Our approach achieves the lowest surface RMSE of~$0.0425$ while maintaining sub-millisecond inference. The quantum layer has zero trainable parameters, sidestepping barren plateaus entirely. Variational quantum methods (VQC, Quantum LSTM) yield negative $R^{2}$ on test data, confirming that fixed quantum feature extractors paired with regularised readouts are more viable for low-data financial applications.