-- Pioneering high-speed, real-time trading strategies and asset management strategy --

Tokyo—Toshiba Corporation, a world leader in applying quantum-inspired optimization solutions to complex real-world problems, has announced the successful development and application of systems based on its simulated bifurcation machine(hereinafter “SBM”), a quantum-inspired optimization computer, to strategy development and execution for financial trading and asset management.

Analysis of the complicated relations and collective structure of many stocks is central to trading and asset management strategies, and can be mathematically formulated as a quadratic discrete optimization problem—a computationally hard problem that is extremely difficult to solve in a short time on classical computers. Toshiba has developed three innovative systems based on SBM, two for high-speed trading and one for asset management, and applied them to analysis of complicated correlations between many stock prices in the Tokyo Stock Exchange (TSE). The results reveal high execution capabilities and effectiveness.

In the world’s first demonstration that orders based on quickly solving computationally hard problems in a constantly changing market, Toshiba used the two high-speed real-time trading systems to find fast solutions to quadratic discrete optimization problems, and to issue buy or sell orders when they detected trading opportunities. The issued orders are filled at the best bid and ask prices (intended prices) used in the decision making.

The asset management system uses the ability of the SBM to quickly find solutions to evaluate a diversified-correlation portfolio strategy. Analysis that applied quadratic discrete optimization to historical data for an unprecedently large group of approximately 2,000 tradable Japanese stocks over a very long period, 10 years, demonstrated that the strategy outperforms major indices, such TOPIX and MSCI Japan Min. Vol.

The high speed and remarkable capabilities of Toshiba’s SBM suit it for application in real-time, edge and embedded, and mission-critical systems. The pioneering results obtained in the current evaluations point the way to the derive other systems that can execute similar strategies, but defined by different measures for risk and return. The detection and execution of trading opportunities among undiscovered correlations in many electronically tradable financial products will contribute to enhanced efficiency in realizing appropriate price formation and liquidity in financial markets by bringing greater liquidity to illiquid stocks.

The details of the three systems were reported in three refereed journal papers^*1, published in the United States in IEEE Access, an open-access journal of the Institute or Electrical and Electronics Engineers, on September 18, October 23 and December 12.

A more comprehensive explanation of the background to this project and the technology deployed is available on the Toshiba Corporate R&D website:

https://www.global.toshiba/ww/technology/corporate/rdc/rd/topics/23/2312-03.html

Acknowledgment

Experiments at the TSE to verify the three systems were conducted in a joint project with Dharma Capital K.K.

• K. Tatsumura et al., “Pairs-trading System using Quantum-inspired Combinatorial Optimization Accelerator for Optimal Path Search in Market Graphs,” IEEE Access 11, pp. 104406-104416, 2023.
  https://doi.org/10.1109/ACCESS.2023.3316727
  K. Tatsumura et al., “Real-time Trading System based on Selections of Potentially Profitable, Uncorrelated, and Balanced Stocks by NP-hard Combinatorial Optimization,” IEEE Access 11, pp. 120023-120033, 2023.
  https://doi.org/10.1109/ACCESS.2023.3326816
  R. Hidaka et al., “Correlation-diversified portfolio construction by finding maximum independent set in large-scale market graph,” IEEE Access 11, 2023.
  https://doi.org/10.1109/ACCESS.2023.3341422