Portfolio Management

According to the Global Industry Classification Standard (GICS), the global asset management industry’s total assets under management (AUM) value at the end of 2020 was approximately $91.7 trillion, managed across 84,000 firms. This consists of the AUM managed by investment firms, pension funds, insurance companies, and other international financial institutions. Frequently, asset managers utilize portfolio management techniques to manage these assets. Investopedia defines portfolio management as follows:

Portfolio management is the art and science of selecting and supervising a portfolio to achieve a specific investment goal for the investor’s benefit.

This chapter will explore the art of portfolio management using machine learning techniques and quantum algorithms. It is divided into five sections:

• Financial portfolio management
• Financial portfolio diversification
• Financial portfolio simulation
• Portfolio management using...

Financial portfolio management

A financial portfolio refers to a collection of assets, including stocks, bonds, and other securities, that an individual or entity invests in to generate a return on investment. Creating a diversified financial portfolio is crucial for investors to minimize risk and maximize returns. A financial portfolio requires careful analysis, market research, and risk assessment.

One of the essential aspects of creating a financial portfolio is diversification. Diversification refers to investing in different types of securities to spread the risk. This strategy aims to reduce the impact of any negative events on the portfolio’s overall performance. For example, a portfolio entirely invested in a single stock or industry may suffer significantly if the company or industry faces challenges. However, a diversified portfolio that includes stocks, bonds, and other securities can help mitigate such risks. Another important factor to consider when building...

Financial portfolio diversification

Financial portfolio diversification is crucial for investors who want to minimize risk and maximize returns. Diversification involves investing in various assets, including stocks, bonds, and other securities, to spread the risk across different markets, sectors, and asset classes. One of the main benefits of financial portfolio diversification is risk reduction. By investing in various assets, investors can avoid the risk of putting all their eggs in one basket. If one asset class or sector performs poorly, other asset classes may perform well, helping to offset losses. For example, if a portfolio is heavily invested in stocks and the stock market crashes, the portfolio’s value may decline significantly. However, if the portfolio also includes bonds, commodities, and real estate, the stock value decline may be offset by gains in other asset classes.

Another benefit of financial portfolio diversification is potential returns. Investing...

Financial portfolio simulation

A financial portfolio simulation is a tool investors use to assess their portfolio’s performance, predict its behavior in the future, and make informed investment decisions. It involves creating a model of an investor’s portfolio and testing different scenarios to determine the best investment strategy. In recent years, portfolio simulation has become increasingly popular because it provides a cost-effective way for investors to assess their risk tolerance and maximize returns. This subsection will examine the concept of financial portfolio simulation, its benefits, and how it can be used to optimize investment decisions.

One of the significant benefits of financial portfolio simulation is its ability to provide investors with a clear understanding of their risk tolerance. By simulating different scenarios, investors can determine their portfolio’s sensitivity to market fluctuations and adjust their investment strategy accordingly...

Portfolio management using traditional machine learning algorithms

Classical implementation

Portfolio optimization is a problem related to the financial services and banking industry that emerged with Markovitz’s seminal paper in 1952 (https://onlinelibrary.wiley.com/doi/full/10.1111/j.1540-6261.1952.tb01525.x). The model describes a set of assets x i ∈ X from which a subset needs to be picked to maximize the revenue, while minimizing the risk at 𝑡 future time steps. For a given period, each asset has an expected return linked to it, and the covariance between assets sets the risk amount in terms of diversification (for the sake of simplicity). The idea behind this diversification is that if we only invest in the assets with the highest revenue, the risk of them being driven by the same factors if our investment fails is bigger than if we diversify our portfolio. We will focus on a single-time-step process, assuming that local optima are part of the longer...

Quantum algorithm portfolio management implementation

Quantum annealers

Quantum annealers are specialized machines capable of finding the minimum energy solution to a given problem, following the adiabatic principle. We talked about some of these machines in Chapter 2, but we will now cover in detail how they can be used to solve a problem such as portfolio optimization.

Quantum annealers require a target problem, set in its matrix form, to place variables as a mask. In our portfolio example, solutions will be encoded as binary decisions if the asset n will be included in our final portfolio. Therefore, our problem matrix should reflect the effect of including an asset or not in a solution.

For this, often in the literature, it is found that problems need to be placed on their QUBO (or Ising) form. QUBO stands for Quadratic Unconstrained Binary Optimization, which means binary variables are considered (0 or 1), only two-way multiplications are represented (X i ×...

Conclusion

When scaling to larger portfolios, computing the optimal result might be too expensive compared to quantum approaches. Still, as we have seen, even when quantum-computing those large combinatorial problems, they come at the cost of needing a complete certainty of the outcome.

It is important to understand that these techniques require, as happens in traditional machine learning approaches, a good understanding of how the best architecture for our ansatz plays in our favor. And in many cases, this will come from the experience of fitting against different types of portfolios and stock combinations. Not all assets show similar behaviors. This will require exploring the vast extension of potential ansatzes, repetitions of schemes in those ansatzes, and optimization techniques that require fewer iterations to find the best parameters.

Even though gate-based quantum devices may offer a generalist approach to quantum computation, it is undeniable that, nowadays, quantum...