From Harvard Business Review
Some industry experts argue that machine learning (ML) will reverse an increasing trend toward passive investment funds. But although ML offers new tools that could help active investors outperform the indexes, it is unclear whether it will deliver a sustainable business model for active asset managers.
Let’s start with the positives
A form of artificial intelligence, ML enables powerful algorithms to analyze large data sets in order make predictions against defined goals. Instead of precisely following instructions coded by humans, these algorithms self-adjust through a process of trial and error to produce increasingly more accurate prescriptions as more data comes in.
ML is particularly adaptable to securities investing because the insights it garners can be acted on quickly and efficiently. By contrast, when ML generates new insights in other sectors, firms must overcome substantial constraints before putting those insights into action. For example, when Google develops a self-driving car powered by ML, it must gain approval from an array of stakeholders before that car can hit the road. These stakeholders include federal regulators, auto insurers, and local governments where these self-driving cars would operate. Portfolio managers do not need regulatory approval to translate ML insights into investment decisions.
In the context of investment management, ML augments the quantitative work already done by security analysts in three ways:
ML can identify potentially outperforming equities by finding new patterns in existing data sets.
For example, ML can sift through the substance and style of all the responses of CEOs in quarterly earnings calls of the S&P 500 companies during the past 20 years. By analyzing the history of these calls relative to good or bad stock performance, ML may generate insights applicable to statements by current CEOs. These insights range from estimating the trustworthiness of forecasts from specific company leaders to correlations in performance of firms in the same sector or operating in similar geographies.
Some of these new techniques produce significant improvements over traditional ones. In estimating the likelihood of bond defaults, for example, analysts have usually applied sophisticated statistical models developed in the 1960s and 1980s respectively by Professors Edward Altman and James Ohlson (notably the Z and O scores). Researchers have found that ML techniques are approximately 10% more accurate than those prior models at predicting bond defaults.
ML can make new forms of data analyzable.
In the past, many formats for information such as images and sounds could only be understood by humans; such formats were inherently difficult to utilize as computer inputs for investment managers. Trained ML algorithms can now identify elements within images faster and better than humans can. For example, by examining millions of satellite photographs in almost real-time, ML algorithms can predict Chinese agricultural crop yields while still in the fields or the number of cars in the parking lots of U.S. malls on holiday weekends.
A flourishing market has emerged for new forms of these alternative datasets. Analysts may use GPS locations from mobile phones to understand foot traffic at specific retail stores, or point of sale data to predict same store revenues versus previous periods. Computer programs can collect sales receipts sent to customers as a byproduct of various apps used by consumers as add-ons to their email system. When analysts interrogate these data sets at scale, they can detect useful trends in predicting company performance.
ML can reduce the negative effects of human biases on investment decisions.
In recent years, behavioral economists and cognitive psychologists have shed light on the extensive range of irrational decisions taken by most humans. Investors exhibit many of these biases, such as loss aversion (the preference for avoiding losses relative to generating equivalent gains) or confirmation bias (the tendency to interpret new evidence so as to affirm pre-existing beliefs).
ML can be employed to interrogate the historical trading record of portfolio managers and analyst teams to search for patterns manifesting these biases. Individuals can then double check investment decisions fitting into these unhelpful patterns. To be most effective, individuals should use ML to check for bias at every level of the investment process – including security selection, portfolio construction and trading executions.
Yet despite these substantial enhancements to investment decisions, ML has its own very significant limitations, which seriously undercut its apparent promise.
To begin with, ML algorithms may themselves exhibit significant biases derived from the data sources used in the training process, or from deficiencies of the algorithms. Although ML will reduce human biases in investing, firms will need to have data scientists select the right sources of alternative data, manipulate the data, and integrate it with existing knowledge within the firm to prevent new biases from creeping in. This is an ongoing process that requires competencies many traditional asset managers don’t currently have.
Secondly, although ML can be very effective at examining huge amounts of past data from one specific domain and finding new patterns relative to an express objective, it does not adapt well to rare situations such as political coups or natural disasters. Nor can ML predict future events if they are not closely related to past trends, such as the 2008 financial crisis. In these cases, investment professionals must make judgments about where future trends are going, based partly on their intuition and general knowledge.
Read the full post at Harvard Business Review.
Robert C. Pozen is a Senior Lecturer at MIT Sloan School of Management and a Senior Fellow at the Brookings Institution.
Jonathan Ruane is a Lecturer in the Global Economics and Management group at the MIT Sloan School of Management and a Digital Fellow at MIT’s Initiative on the Digital Economy (IDE).