Quantum Machine Learning for Multi-Asset Price Prediction

In this paper, we apply quantum machine learning (QML) to predict the stock prices of multiple assets using a novel context-based quantum neural network. Unlike previous approaches that focus on modeling entire historical data distributions, our method predicts future stock price distributions by capturing recent trends, leading to greater adaptability and precision. Leveraging quantum superposition and linearity, we introduce a conditional fidelity loss for training quantum neural networks over loaded distributions that significantly accelerates the training process and increases the scalability over context distributions. Consequently, we propose a novel quantum multi-task learning (QMTL) architecture that integrates task-specific operators controlled by quantum labels, enabling the simultaneous and efficient training of multiple assets on the same quantum circuit as well as enabling efficient portfolio representation with logarithmic overhead. This architecture represents the first of its kind in quantum finance, offering superior predictive power and computational efficiency for multi-asset stock price forecasting. Our findings highlight the transformative potential of QML in financial applications, paving the way for more advanced, resource-efficient quantum algorithms in stock price prediction.