Skip to Content

Machine learning's role in the hunt for alpha

Este artículo está disponible sólo en inglés.

As soon as the vast “neural network” of algorithms hummed to life, the portfolio managers (PMs) began to extract from it knowledge and investment recommendations. When they were skeptical of the wisdom of a suggestion to buy or sell a stock, the PMs nudged their proprietary machine to better appreciate the economic rationales for investing. And it would learn. A virtuous cycle, undertaken to boost long-term investment results for Vanguard shareholders, was born.

Our actively managed equity funds that employ machine learning (ML)—and their shareholders—are starting to benefit, according to Cesar Orosco, CFA, and Scott Rodemer, CFA, of Vanguard’s Quantitative Equity Group (QEG). The group develops quantitative models that attempt to replicate what a good fundamental investor would do, but systematically and at scale.

“There are a few ways machine learning has tended to boost alpha,” or marginal returns above those of a portfolio’s benchmark, said Rodemer, head of factor-based strategies. “For example, alpha exposures have become more dynamic; growth signals more price sensitive; and sources of excess returns more intertwined.”

As intended, neither portfolio turnover nor aggregate measures of portfolio risk, such as tracking error relative to a benchmark, have changed appreciably. 

Identifying patterns in complex, noisy financial data 

Financial practitioners never have enough clearly actionable data, said Orosco, head of alpha equity investments. “Markets are incredibly noisy, so extracting the signal from the noise is quite the challenge.”

Through dogged research and testing, however, a QEG project team and members of Vanguard’s “AI Garage”—a community of artificial intelligence (AI)/machine learning practitioners from across the company—have found that using ML consistently added value in simulated portfolios. Complex relationships among economic and financial market conditions and the performance of individual companies and their stocks were clarified—if only a bit. 

To be sure, the introduction of machine learning to a portfolio management process is no guarantee of stronger results, and ML-based recommendations remain imperfect. “But we are a systematic manager,” said Orosco. “We diversify widely, and in our business, being right 55%–60% of the time over extended periods can add significant long-term value for investors.” 

Integrating machine learning into an established investment process

QEG’s U.S. alpha team employs an ensemble model—really, a collection of dozens of models tracking tens of millions of underlying economic and financial market interactions. Overall, half the inputs come from the team’s traditional approach, refined over decades, and half from ML. 

The ML-driven output doesn't rely on entirely new signals, however. Said Rodemer: “From the beginning we engrained fundamental reasoning into the model, an understanding of what adds value to a company and influences future returns—concepts like valuations, growth, and profitability—and embedded this intuition into a proprietary deep neural net architecture.” A key new element is ML’s continual interpretation of the macroeconomic environment, as context for company- and stock-specific changes.

While the PMs naturally remain responsible for all investment choices, they lean heavily on model signals to make virtually all buy, sell, and rebalancing decisions for three U.S. equity portfolios that are managed entirely by QEG. 

Making sense of ML-based investment recommendations

Before integrating machine learning into the management of Vanguard fund assets, Orosco and Rodemer and their colleagues set a high bar: They had to be able to understand why the algorithms would recommend any given investment. 

“We won’t trade on signals that we don’t understand,” said Rodemer. “Everything has to tie back to a fundamental rationale.” 

That’s why the team built an “interpretability model” that gives PMs—as well as Vanguard’s independent portfolio review and risk-management teams—explanations of:

  • The drivers of individual stock predictions. 
  • The aggregate-level interpretations of model behavior (such as the sensitivity of the signals to macroeconomic changes). 
  • The model health analytics (such as the volatility of scores and outliers in daily model changes), which help the team assess model inputs and outputs. 

“We believe the foundations are solid, the experimentation was solid, and the improvements so far continue to be in line with expectations,” said Orosco. “So as long as that continues, we're going to be comfortable moving forward.” 

Notes:

For more information about Vanguard funds, visit vanguard.com to obtain a prospectus or, if available, a summary prospectus. Investment objectives, risks, charges, expenses, and other important information about a fund are contained in the prospectus; read and consider it carefully before investing.

All investing is subject to risk, including the possible loss of the money you invest. Diversification does not ensure a profit or protect against a loss. Be aware that fluctuations in the financial markets and other factors may cause declines in the value of your account. There is no guarantee that any particular asset allocation or mix of funds will meet your investment objectives or provide you with a given level of income.

Prices of mid- and small-cap stocks often fluctuate more than those of large-company stocks.

CFA® is a registered trademark owned by CFA Institute.