Quantum Temporal Convolutional Neural Networks for Cross-Sectional Equity Return Prediction: A Comparative Benchmark Study

TL;DR

The paper tackles robust stock return forecasting under noisy, dynamic conditions by introducing QTCNN, a hybrid quantum-classical model that combines a classical temporal encoder with parameter-efficient quantum convolution. It benchmarks QTCNN against multiple quantum and classical baselines on the JPX Tokyo dataset, using out-of-sample Sharpe ratio as the primary metric. Results show QTCNN achieving an out-of-sample Sharpe of 0.538, about 72% higher than the best classical baseline, highlighting the potential of quantum-enhanced forecasting for quantitative finance. The study also provides a reproducible benchmark framework and clear design principles for integrating quantum circuits with time-series features, paving the way for future hardware-oriented validation and broader market testing.

Abstract

Quantum machine learning offers a promising pathway for enhancing stock market prediction, particularly under complex, noisy, and highly dynamic financial environments. However, many classical forecasting models struggle with noisy input, regime shifts, and limited generalization capacity. To address these challenges, we propose a Quantum Temporal Convolutional Neural Network (QTCNN) that combines a classical temporal encoder with parameter-efficient quantum convolution circuits for cross-sectional equity return prediction. The temporal encoder extracts multi-scale patterns from sequential technical indicators, while the quantum processing leverages superposition and entanglement to enhance feature representation and suppress overfitting. We conduct a comprehensive benchmarking study on the JPX Tokyo Stock Exchange dataset and evaluate predictions through long-short portfolio construction using out-of-sample Sharpe ratio as the primary performance metric. QTCNN achieves a Sharpe ratio of 0.538, outperforming the best classical baseline by approximately 72\%. These results highlight the practical potential of quantum-enhanced forecasting model, QTCNN, for robust decision-making in quantitative finance.