Evolving Hedging for a Quantum Future

As Global Technology Applied Research at JPMorgan Chase, we’re conducting research today that will help the bank excel in the financial services landscape of tomorrow.

Our latest research[MEG1]  demonstrates the potential viability of quantum “deep hedging.” Examined in partnership with QC Ware, this application paves the way for future increased risk mitigation capabilities in financial
services.

This research examines how deep hedging—reducing risk for a portfolio utilizing data-driven models that consider market frictions and trading constraints—might be improved
with quantum computing.

We began our research by first examining whether classical deep hedging frameworks could be improved using quantum deep learning. Then, using quantum reinforcement learning, we studied whether a new quantum framework could be defined for deep hedging. Our findings indicate that deep hedging on classical frameworks using quantum deep learning enables models to be trained more efficiently.

Deep hedging on new quantum frameworks also enables quantum value functions to:

• Efficiently learn the expectation and distribution of returns
• Offer improved performance via a quantum actor-critic reinforcement learning model
• Appropriately train quantum policies 

Leveraging quantum machine learning methods will be helpful in financial services as quantum computing becomes more commercially accessible. It’s exciting to see how this research is laying the groundwork for potential ways to mitigate risk in financial services in the future.

Read the press release here.

To learn more
about Global Technology Applied Research at JPMorgan Chase, please visit https://www.jpmorgan.com/technology/applied-research.