The Behavioral Frontier of Active Investment Management
0 min read
I’m sure many of you are familiar with the 2011 hit movie Moneyball, featuring superstars Brad Pitt and Jonah Hill. The film, centering around the Oakland Athletics baseball team, gives an account of how manager Billy Beane transforms the team’s performance, despite having the lowest payroll in the major leagues.
Moneyball tells the tale of an underdog's rise to glory using data analytics, now a multimillion-dollar industry that has revolutionized sports. More recently, data analytics is proving its worth once again, this time within the investment management industry. Behavioral data analytics is helping portfolio managers to fine-tune their decision-making process, giving them a vital competitive advantage. This is done with the help of machine-learning algorithms that can analyze large data sets of historical investment data to detect behavioral patterns that are either adding or destroying value within a portfolio.
Why investment managers need to up their game
Following a surge in the popularity of low-fee index funds, the active management industry has been feeling the pressure. To justify the fees that investment managers charge, they must outperform the index net of fees — i.e., they must earn the same return as the index plus the cost of the fees they charge.
This is where behavioral data analytics can help. Decision-making in such a high-stake industry can have huge monetary consequences. By treating the decision-making process of PMs (portfolio managers) as a set of skills that can be analyzed and refined, data analytics can aid behavior change to boost a portfolio’s “behavioral alpha” — the excess investment return that results from mitigating the cognitive biases hidden in the investor’s decision-making process. This combination of behavioral science and data analytics can pinpoint value-destroying behavior and provide portfolio managers with the information and tools needed to enhance their decision-making process.
Behavioral Science, Democratized
We make 35,000 decisions each day, often in environments that aren’t conducive to making sound choices.
At TDL, we work with organizations in the public and private sectors—from new startups, to governments, to established players like the Gates Foundation—to debias decision-making and create better outcomes for everyone.
Cognitive biases hinder investment decisions
The Efficient Markets Hypothesis states that share prices reflect all available information, consequently making it impossible to beat the market. The stock market of the real world, however, is another story: created and driven by human behavior, it is riddled with cognitive biases.
Here are just a few of the mostly influential biases at play in investment decisions:
The endowment effect
The endowment effect causes people to overvalue what they already own. It is an affliction that can cause investment managers to hold onto stocks after they have passed their peak profitability, or even when their value is declining.
PMs, like the rest of us, measure their performance through comparison. Alpha is the excess return they earn in comparison to a benchmark index of similar stocks. Active managers who avoid the endowment effect and exit at or near the peak profitability point, rather than holding into the decline phase, can outperform index funds well in excess of their fees. Ultimately, knowing when to sell is just as important as knowing what to buy.
Loss aversion states that people do not equate losses and gains equally and that we will go to great lengths to avoid a loss. As a novice trader myself, I find that when one of my stocks is declining I often misguidedly believe that it will somehow bounce back — a strategy that has not served me well, and as a result I have decided not to quit my day job.
It is easy to fall victim to emotions while trading and seek that adrenaline fueled high of soaring prices. But in the words of the famous investor Warren Buffet, “If you cannot control your emotions, you cannot control your money.” This is a testament to the value behavioral analytics can add to investing by encouraging rational rather than emotional decision-making.
Overconfidence bias is the tendency to overestimate our abilities. This bias often manifests in over-trading. You should only make a trade if you believe you have a greater than 50% chance of being right. However it is often the case that PMs only do as good as or worse than this 50:50 chance.
Regret aversion is the avoidance of decisions that could cause future regret can synonymously be damaging to an investment portfolio. It can cause PMs to enter or exit a stock slowly, missing out on the best price due to their hesitance.
Giving investment managers a nudge over the line
There are three pillars to recognize and mitigate these behavioral biases: data analytics, tailored nudges, and specialist coaching. These elements work in concert to provide a powerful feedback loop for active investment decisions, helping investors attain better outcomes from their investment choices.
First, bleeding-edge algorithms are used to analyze years of historical investment data, in order to pinpoint the decision-making deficiencies and cognitive biases to which an individual client is most prone. Armed with this information, the PM can then schedule context-specific nudges to be sent to them when destructive patterns of behavior are emerging in the portfolio.
These nudges are tailored prompts to consider and/or execute an element of the manager’s decision-making process, asking them to answer a predefined list of questions they have devised for when a specific pattern emerges. When nudged to consider these questions, PMs shift their financial decision-making processes from System 1 of the brain, where automatic and unconscious decisions are made, to System 2, where complex decisions are logically thought out. This enables them to make more deliberate decisions at key points in time.
Coaching on and off the trading floor
Investment managers, despite their years of experience, are not immune from these human pitfalls. Cognitive bias can creep into PMs’ decisions and sabotage key skills directly tied to alpha generation/loss within portfolios. These include:
- Entry and Exit Timing
- Scaling In and Out
- Stock Picking
- Size Adjusting
Thankfully, through training, managers can learn to recognize destructive patterns in their own decision-making and develop skills to counteract these tendencies. Finding a specialist coach — somebody who is an expert in behavioral analytics and who is familiar with the ins and outs of investment management — lets PMs receive individualized guidance and continually improve their decision-making over time.
Through coaching, investment managers can learn to recognize where these biases are at play within their investment decisions and how to avert potentially destructive behaviors.
Case Study: Behavioral investment management at Essentia Analytics
The techniques above make up the three-pronged approach we use at Essentia Analytics. It has resulted in increased alpha generation by an average of 150 basis points per year after 12 months on the platform for our clients. For context, that equates to an additional $1.5 million return on a fund of 100 million AUM (assets under management), most of which goes back to investors. Our research has also found that on average, every monthly response to a personalized nudge correlates with an additional 18bps (0.18%) of alpha per year.
At Essentia, clients are matched with coaches known as Insight Partners. Trained experts in interpreting the bespoke analytics and former fund managers themselves with a wealth of hands-on investment knowledge, Insight Partners are uniquely qualified to coach PMs through the improvement process. They meet with PMs on a regular basis to explain the insights found within the data and to formulate and manage ongoing action plans. You might say they are the Billy Beanes of the investment industry.
Through a combination of coaching and nudging, Essentia partners with clients to mitigate behavioral bias, optimize investment processes, and measurably improve decision-making on an ongoing basis. This approach takes behavioral finance and behavioral analytics from the confines of university classrooms — and pro sports offices — and converts decades of research into real-life behavioral change among portfolio managers … with real-world benefits to investors.
A final word
We live in a society that strives for constant growth and improvement in all aspects of life. Now, we have the analytical tools to facilitate a data-driven feedback loop for continuous improvement in investment management. At the intersection of AI and behavioral science, a new frontier of investment management has emerged.
In the words of the late pioneer of decision research Amos Tversky, “Whenever there is a simple error that most laymen fall for, there is always a slightly more sophisticated version of the same problem that experts fall for.” In the case of investment managers, these cognitive errors are worth millions of investors' money. I think we would all sleep better at night knowing our pensions were in the hands of a self-aware and diligent investor whose decisions were grounded in science and data, not merely in intuition.
Further information on this topic can be found here:
- The Essentia Blog: https://www.essentia-analytics.com/essentia-blog/
- Essentia White Papers & Case Studies: https://www.essentia-analytics.com/essentia-white-papers/
- Common Investment Biases: https://www.essentia-analytics.com/common-behavioral-biases/
What is Behavioral Alpha? (n.d.). Essentia Analytics. https://www.essentia-analytics.com/about-essentia/behavioral-alpha/
Kahneman, D. (2012). Thinking, Fast and Slow. Farrar, Straus and Giroux.
Kahneman, D., & Tversky, A. (1979). Prospect Theory: An analysis of decision under risk. Econometra, 49.
Woodcock, C. (n.d.). What's in a Nudge. Essentia Analytics. https://www.essentia-analytics.com/whats-in-a-nudge/
About the Author
Eva holds a Bachelor of Science Mathematics degree and is currently undertaking a Master's in Cognitive and Decision Science at University College London. She is a committee member for UCL’s Behavioral Innovations Society, a student community of behavioral scientists that aims to deliver positive and sustainable behavior change within UCL and beyond. She also works for Essentia Analytics, a behavioral data analytics service that helps investment managers make measurably better investment decisions. Standing at the precipice of major technological upheaval she believes it is essential to apply behavioral science research to new technological advancements.