Using Quantum Annealing To Build Stronger Stock Portfolios
By IEEE Computer Society Team on
Quantum annealing (QA) has emerged as an effective way to find the optimal solution using a large dataset. While this has applications in an endless variety of use cases, its application in the realm of finance may be one of the fastest ways for researchers to realize a significant ROI in their annealing work.
Yao-Hsin Chou, Ching-Hsuan Wu, Pei-Shin Huang, Jyun-Yi Shen, of National Chi Nan University, Department of Computer Science and Information Engineering, Shu-Yu Kuo, Sy-Yen Kuo, of the National Taiwan University, Department of Electrical Engineering, and Ching-Ray Chang of Christian University, Department of Physics, recently explored ways to use quantum annealing to enhance the management of international stock portfolios.
What Is Quantum Annealing?
Quantum annealing uses quantum properties to determine an optimal solution. Since the qubits in quantum computers, unlike traditional computing algorithms, have the quality of superposition, they can explore many possibilities simultaneously. Superposition is a quality that allows a quantum particle to exist in multiple states — and be in multiple places — at the same time. This gives a quantum annealing computer the ability to identify optimal solutions very quickly because it can evaluate many possibilities simultaneously.
Also, thanks to quantum tunneling, quantum annealing is far less likely to prematurely identify a “good” instead of an “excellent” solution. A quantum annealing computer can examine many solutions simultaneously, compare them to each other, and choose the most optimal one.
Why Quantum Annealing Benefits Stock Portfolio Analysis
Quantum annealing can evaluate large datasets for stock portfolio analysis. It can then determine which stocks are likely to perform well in a given situation.
This is because the quantum annealing process involves using large amounts of data to identify an optimal state. Pharmaceutical researchers can utilize quantum annealing to identify the best protein to use in a drug, making it easier to choose proteins for use in medications.
When choosing which stocks to include in portfolios, quantum annealing can demonstrate stronger performance when it comes to:
- Daily profit factor (DPF). The QA process can determine which stocks are consistently the most profitable daily.
- Maximum drawdown (MDD). Lower maximum drawdowns indicate less risk. Using QA, portfolio managers can more accurately determine which stocks have lower MDDs and choose them for risk-averse clients.
- Trend ratio (TR). Using QA, researchers can determine which stocks align best with specific trends in terms of performance. If a trend is going up, for instance, QA can identify which stocks tend to rise in tandem, and vice versa.
According to the paper, quantum annealing also excels in identifying high-performance portfolios within a relatively short period of time. This can prevent analysts from mistakenly identifying underperforming portfolios, mislabeling them, and, therefore, reducing the overall value of their firm’s or client’s general portfolio.
How To Use QA in Stock Portfolio Management
Since quantum annealing outperforms traditional analytical methods, researchers can use it to produce results superior to those generated by older techniques and algorithms. For instance, using QA, a portfolio analyst can:
- Identify portfolios that can have the most positive effect on a firm’s daily profit margins
- Analyze maximum drawdown to eliminate high-risk stocks from portfolios used in more conservative investment strategies
- Advise portfolio managers regarding which stocks to choose according to current or future trends.
For instance, if the U.S. dollar is in the midst of an uptrend, an analyst could use a QA report to advise a portfolio manager on which stocks are most likely to rise in tandem with the dollar.
Quantum Annealing: A Powerful New Tool in Stock Portfolio Management
Although QA can’t predict the future, researchers have demonstrated its superiority when compared to traditional analytical tools. This may pave the way for utilizing QA to reduce risk and boost profits by leveraging large amounts of stock portfolio performance data. Even if QA produces marginally better portfolio performances, this can result in hundreds of thousands of dollars in additional profits for financial companies and their clients.
Disclaimer: The author is completely responsible for the content of this article. The opinions expressed are their own and do not represent IEEE's position nor that of the Computer Society nor its Leadership.
