In a new paper released March 30, JPMorgan Chase and QC Ware examine two questions about how the practice of deep hedging—reducing risk for portfolios that leverage data-driven models that take into account market frictions and trading constraints—can be enhanced by quantum computing. The researchers first examined whether existing classical deep hedging frameworks could be enhanced using quantum deep learning. Then, using quantum reinforcement learning, they studied whether new quantum frameworks could be specified for deep hedging.
This study found that hedging the depth on a classical framework using quantum deep learning allows the model to be trained more efficiently. The research, conducted on the H1-1 Quantinuum quantum computer, also demonstrates the potential for future computational acceleration, which could be implemented on noisy mid-scale quantum hardware (NISQ). Deep hedging in the new quantum framework also allows quantum value functions to:
Study the expectations and efficient distribution of returns
Offers increased performance through learning models of quantum actor-critic reinforcement
Practice quantum wisdom properly.
Quantum applications can offer enhancements for deep hedging in both classical and quantum environments—they leverage quantum machine learning methods to increase accuracy and trainability on high-performance GPU hardware, which will help in financial services as quantum computing becomes more accessible commercially .
“We hedged the depths for the next logical evolutionary step,” says Iordanis Kerenidis, head of Quantum Algorithms at QC Ware. “The results achieved with JPMorgan Chase demonstrate the huge potential and applications of quantum machine learning, both today, by using quantum ideas to provide new models with classical hardware, as well as leveraging the ever more powerful quantum hardware we anticipate. in the future.”
“As quantum computing matures, JPMorgan Chase’s leading position will only be further strengthened through future-ready algorithms that will deliver ever-increasing yields,” said Marco Pistoia, Managing Director, Head of Global Technology Applied Research, JPMorgan Chase. “We are pleased to further optimize our existing sterling hedging strategy, not only to provide value for investors, but also to enable more frequent and sophisticated hedging positions in the market. This work helps pave the way for banks to incorporate quantum computing into deep hedges.”
Read the full research paper Here.