Paper Implementation Challenge : Quantum-enhanced portfolio optimization framework

[rizanuma]

Hi team,

This PR introduces a quantum-enhanced portfolio optimization framework based on the Black-Litterman model, integrated with QAOA and VQE using Classiq’s automated quantum circuit synthesis.

Summary:

• Implements Black-Litterman-based QUBO formulation for asset allocation.

• Uses Classiq to optimize circuit depth and automate qubit mapping.

• Applies VQE for asset selection and QAOA for portfolio optimization.

• Supports scalability beyond 12 qubits and secure computation with homomorphic encryption.

• Includes comparison with classical models and walk-forward backtesting.

Based on the Black-Litterman framework by He & Litterman (1999), integrating market equilibrium with investor views.

Please let us know if you have suggestions for enhancing performance evaluation or improving the Classiq integration. Feedback on the quantum-classical hybrid orchestration or on potential edge cases in asset selection would be especially valuable.

Thanks in advance for your time and insights! 🙌

[TomerGoldfriend]

@rizanuma thank you very much for this PR. Please follow the Contribution Guidelines, you are supposed to provide an .ipynb file including explanations, and not a single python file.

A clarification question: are you applying a standard QAOA for portfolio optimization, where the QUBU matrix is derived from some non-trivial classical pre-process on real data?

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[rizanuma]

hey @TomerGoldfriend , i've addressed your review comments.