[challenge]: Using quantum machine learning to predict the financial market trends and demonstrate quantum advantage

Released by

Junkai Wang

Contact email

WangTheoPhys@outlook.com

Method

Quantum Circuit Simulation

Challenge issue

Demonstrating quantum advantage in real-world tasks and practical scenarios is a problem of great concern to the entire academic and industrial communities of quantum artificial intelligence and quantum scientific computing. The financial market has received widespread attention due to its unique characteristics. Recently, even in the top physics journal Physical Review Letters, there was an article about demonstrating scaling in financial market prediction. It serves as an exceptional practical testing ground that spans finance, trading, and scientific uncertainty and prediction.

While many proposals utilizing quantum methods for financial market prediction have already been put forward, our goal is to explore how to design better methods. Such methods must necessarily incorporate the characteristics of financial markets, such as data scale and noise size, which vary across long-range and short-term horizons as well as different tasks.

Our mission is to design a strong algorithm that can outperform classical benchmarks, baselines, and similar quantum algorithms, thereby demonstrating quantum advantage with the prospect of realization on near-term quantum hardware.

The issue names no repository files, tests, datasets, or entry points, so first inspect the repository to find the quantum circuit simulation and evaluation setup. Define the financial prediction task and compare the proposed method with classical, baseline, and similar quantum algorithms. Done means reproducible evidence that the method outperforms those benchmarks and demonstrates quantum advantage.