Quantum Annealing for Clustering Signed Financial Correlation Networks

Summary

The document describes using the Graph-based Coalition Structure Generation algorithm, GCS-Q, to cluster assets represented as a signed, weighted graph of return correlations. The motivation is that common clustering approaches can lose information when they transform signed correlations and may require the number of clusters to be chosen in advance. GCS-Q instead formulates partitioning steps as quadratic unconstrained binary optimization problems, which can be explored with quantum annealing.

The authors evaluate the approach on synthetic and real-world financial data and compare it with SPONGE and k-Medoids. They report higher clustering quality by Adjusted Rand Index and structural balance penalties, while the method determines cluster count dynamically. The description gives no dataset specifics, numerical results, runtime comparisons, or details about quantum hardware and implementation. Its reported gains support the method as a research direction for portfolio optimization and statistical arbitrage, but do not by themselves show that it improves trading outcomes or is practical at all asset-universe sizes.

Key ideas

• GCS-Q clusters assets directly from signed, weighted correlation graphs.
• Its partitioning steps are expressed as QUBO problems for quantum annealing.
• The method dynamically determines the number of clusters.
• Experiments on synthetic and real-world data are reported to outperform SPONGE and k-Medoids on stated clustering measures.
• The document does not establish effects on portfolio returns or trading performance.

Tags

# Toward Quantum Utility in Finance: A Robust Data-Driven Algorithm for Asset Clustering


# Toward Quantum Utility in Finance: A Robust Data-Driven Algorithm for Asset Clustering









Clustering financial assets based on return correlations is a fundamental task in portfolio optimization and statistical arbitrage. However, classical clustering methods often fall short when dealing with signed correlation structures, typically requiring lossy transformations and heuristic assumptions such as a fixed number of clusters. In this work, we apply the Graph-based Coalition Structure Generation algorithm (GCS-Q) to directly cluster signed, weighted graphs without relying on such transformations. GCS-Q formulates each partitioning step as a QUBO problem, enabling it to leverage quantum annealing for efficient exploration of exponentially large solution spaces. We validate our approach on both synthetic and real-world financial data, benchmarking against state-of-the-art classical algorithms such as SPONGE and k-Medoids. Our experiments demonstrate that GCS-Q consistently achieves higher clustering quality, as measured by Adjusted Rand Index and structural balance penalties, while dynamically determining the number of clusters. These results highlight the practical utility of near-term quantum computing for graph-based unsupervised learning in financial applications.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.