Quantitative risk management, particularly volatility forecasting, is critically important to traders, portfolio managers as well as policy makers. In this paper, we applied quantum reservoir computing for forecasting VIX (the CBOE volatility index), a highly non-linear and memory intensive ‘real-life’ signal that is driven by market dynamics and trader psychology and cannot be expressed by a deterministic equation. As a first step, we lay out the systematic design considerations for using a NISQ reservoir as a computing engine (which should be useful for practitioners). We then show how to experimentally evaluate the memory capacity of various reservoir topologies  (using IBM-Q’s Rochester device) to identify the configuration with maximum memory capacity. Once the optimal design is selected, the forecast is produced by a linear combination of the average spin of a 6-qubit quantum register trained using VIX and SPX data from 1990 on wards. We test the forecast performance over the subprime mortgage crisis period (Dec 2007-Jun 2009). Our results show a remarkable ability to predict the volatility during the Great Recession using today’s NISQs.

Samudra Dasgupta obtained his B.Tech in Electronics and Electrical Engineering from IIT-Kharagpur 2006, followed by M.S. in Engineering and Applied Sciences from Harvard 2008 and an M.B.A. from Indian School of Business 2012; He has over 10 years of work experience in various financial organizations indifferent capacities, including in Goldman Sachs (Vice President, Liquidity Risk Management), McKinsey and Company, (Engagement Manager, Banking and Finance), Bank of America (Assistant Vice President, Corporate Investments Group) and Higher Moment Capital (Research Analyst at Quant Hedge Fund). He is currently an entering Ph.D. candidate at the Oak Ridge National Laboratory's Quantum Computing Institute and the Bredesen Center University of Tennessee-Knoxville and during the past year, he has also been a Research Associate with Purdue University and ORNL. His current research interest is on the applications of quantum algorithms and NISQ in the prediction and mitigation of financial problems.

Purdue Quantum Science and Engineering Institute, Discovery Park

Researchers should cite this work as follows:

• S. Dasgupta, K. Hamilton, A. Banerjee, Designing a NISQ reservoir with maximal memory capacity for volatility forecasting, 2020, https://arxiv.org/abs/2004.08240

• Samudra Dasgupta (2020), "Designing a NISQ Reservoir with Maximal Memory Capacity for Volatility Forecasting," https://nanohub.org/resources/34421.

  BibTex | EndNote

1. algorithms
2. forecasting
3. IBM-Q
4. joes picks
5. NISQ reservoir
6. quantum computing
7. quantum science and information
8. risk assessment and management