Question Clustering: Ensuring relevance and rigor in business and geopolitical forecasting

Forecasting is an essential part of business. Companies use historical data and economic trends to make informed estimates of future sales, profits, and losses. Amazon and Google rely on predictive algorithms to highlight specific products or search results for their customers. Shopkeepers arrange their display windows based on their predictions of demand. Some of the forecasting is narrow and company-specific. The more challenging part has to do with broader questions, such as the overall market outlook.

Consider this question: What will market conditions be like after the pandemic?

This question is of great relevance to any business decision-maker, but it’s so broad that it could be approached from many different angles, using multiple definitions. “Market conditions,” for instance, involves multiple factors, from industry-specific trends to interest rates, from consumer spending to supply chains. How do we intend to measure this? What time frame are we looking at?

Much more tractable is a narrower question—”On 31 January 2022, what will be the average US tariff rate on imports from China?” But in checking all the boxes to craft a rigorous question, narrow topics may lose their relevance to decision-makers trying to determine the prospects for their business down the line. This is the rigor-relevance trade-off.

To tackle the relevant strategic questions that decision-makers ask with the rigor that accurate forecasting requires, Good Judgment crafts sets of questions about discrete events that, in combination, shed light on a broader topic. Good Judgment calls this technique question clusters. Good clusters will examine the strategic question from multiple perspectives—political, economic, financial, security, and informational. These days, a public health perspective is also usually worthwhile. Aggregating the probabilities that the Superforecasters assign to such specific questions generates a comprehensive forecast about the strategic question, as well as early warnings about the deeper geopolitical or business trends underway.

The Good Judgment team developed this method in a research study sponsored and validated by the US Intelligence Advanced Research Projects Activity from 2011-2015, where the Superforecasters outperformed the collective forecasts of intelligence analysts in the US government by 30%. Since then, the Superforecasters have refined and expanded their approach to evaluate emerging consumer trends, inform product development, and understand the factors driving commodity markets. A similar framework was detailed in a recent Foreign Affairs cover article by Professor Philip Tetlock and Dr Peter Scoblic.

As an example, a question cluster on a critical topic that clients have asked Good Judgment to develop includes political, military, social, and economic forecasts on emerging trends regarding Taiwan:

• • Will Taiwan accuse the People’s Republic of China (PRC) of flying a military aircraft over the territory of the main island of Taiwan without permission before 31 December 2021?
  • Will the PRC or Taiwan accuse the others’ military or civilian forces of firing upon its own military or civilian forces before 1 January 2022?
  • Before 1 January 2022, will US legislation explicitly authorizing the president to use the armed forces to defend Taiwan from a military attack from the PRC become law?
  • Will Taiwan (Chinese Taipei) send any athletes to compete in the 2022 Winter Olympics in Beijing?
  • Will the Council of the EU adopt a decision authorizing the Commission to open negotiations with Taiwan on an investment agreement?
  • Will the World Health Organization reinstate Taiwan’s observer status before 1 January 2022?

As another example, in forecasting the technological landscape, the Superforecasters estimate the emerging trends in electric car sales, hydrogen-fueled vehicles, the growth of Starlink services, and social media regulation, among others.

Independently, these forecasts are crucial for some companies and investors and informative for the discerning public. Taken together, they point to trends that are shaping the future of the geopolitical and business world.

The same technique can be applied to Amazon. The traditional approach of security analysts is to build a fixed model that predicts valuation based on dividends, cash flow, and other objective metrics. A question cluster approach can uncover critical subjective variables and quantify them, such as the risk of a regulatory crackdown or shifts in labor relations, to make the analyst’s model more robust.

“In business, good forecasting can be the difference between prosperity and bankruptcy,” says co-founder of Good Judgment, Professor Philip Tetlock. Successful businesses rely on forecasting to make better decisions. Using clusters of interrelated questions is one way to ensure those forecasts are both rigorous and relevant.

* This article originally appeared in Luckbox Magazine and is shared with their permission.

The Cost of Overconfidence

With SPACs all the rage, it’s important not to be too carried away by the rhetoric. Overconfidence can be expensive. This is true in geopolitics, public health, or the stock market. From the 1961 Bay of Pigs debacle to the slow response to the COVID-19 crisis, to millions of dollars lost speculating in the markets, history is filled with costly examples. And yet, bold statements continue to be overvalued in our culture. Time and time again, the media turn to pundits who speak with conviction despite their spotty track records when it comes to offering real foresight.

Think back to a year ago, when the airwaves were filled with experts and politicians confidently asserting that COVID-19 would swiftly pass. The US president claimed in February 2020 that the coronavirus was under control in the US and would disappear “like a miracle.” It took another month for the administration to acknowledge that the unfolding pandemic was serious.

“A confident yes or no is satisfying in a way that maybe never is, a fact that helps to explain why the media so often turn to hedgehogs who are sure they know what is coming no matter how bad their forecasting records may be,” writes Good Judgment’s co-founder Philip E. Tetlock in his book with Dan Gardner, Superforecasting: The Art and Science of Prediction.

Dr. Tetlock refers to a distinction between “foxes” and “hedgehogs,” a metaphor borrowed from ancient Greek poetry and popularized by the philosopher Isaiah Berlin: “The fox knows many things but the hedgehog knows one big thing.”

Hedgehogs tend to be more confident—and more likely to get media attention—but, as research has found in multiple experiments, they also tend to be worse forecasters. Foxes, in contrast, tend to think in terms of “however” and “on the other hand,” switch mental gears, and talk about probabilities rather than certainties.

For instance, last year Good Judgment’s Superforecasters were estimating with a 67% probability that worldwide cases of COVID-19 would exceed 53 million within a year and a 99% probability that deaths in the US alone would be more than 200,000—a figure many found exorbitant at the time. Superforecasters proved right in both cases. Their judgment was, and continues to be, well-calibrated. In other words, they know what they know and know what they don’t know, and they make their forecasts accordingly.

To avoid overconfidence, Superforecasters consider worst-case scenarios. Instead of relying on hunches and past success, they actively seek out evidence that those hunches may be wrong. They embrace new information and are not afraid to change their mind in light of new evidence.

Alas, pundits and most of the media have yet to join the foxes. “We live in a world that rewards those who speak with conviction—even when that is misplaced—and gives very little airtime to those who acknowledge doubt,” writes Financial Times columnist Jemima Kelly.

The sense of security that comes with confident judgments is comforting. But it is an illusion.

The cost of that illusion can be steep: from the inadequate early response to the pandemic to the investors trading to their detriment because they are overconfident about their ability to predict stock market returns.

Superforecasters know a way to avoid that cost: In a world that overvalues hedgehogs, pay more attention to your inner fox.

* This article originally appeared in Luckbox Magazine and is shared with their permission.

Open-Minded Forecasting in a Deeply Polarized World

Americans today are more polarized than ever, and their split along two ideological extremes complicates a forecaster’s job. Polarization stresses feelings over facts, confounding the separation of signal from noise that’s essential to forecasting accuracy. Also, the forecaster’s own biases and preferences can be harder to recognize—and set aside—when society at large is polarized and the outcomes are personally consequential.

When Good Judgment Inc, a forecasting company with an unrivalled track record of accuracy, asked its professional Superforecasters to predict the outcome of the 2020 US election cycle, these challenges were front and center. Many Superforecasters live in the United States and feel deeply about political issues in the country. Some of them worried this could cloud their forecasting judgment. But Superforecasters thrive in the face of challenges. Here is what they did, and what you can do to improve the accuracy of your own predictions in a polarized world.

US Election 2020: Getting It Right

On the question of the presidency, the Superforecasters ­predicted a Democratic win of the White House in March 2020 and never looked back. On control of Congress, they began predicting both the House and Senate would go to the Democrats as early as June. Furthermore, they accurately called:

• • the long-delayed concession,
  • the record voter turnout, and
  • the Democrats’ presidential fundraising edge as of 30 September.

But getting it right is only half of the picture. Good Judgment strives not only to be right but also to be right for the right reasons. When polarization abounds, this is all the more important. To calibrate their thinking, Superforecasters use three simple strategies that consistently result in more accurate predictions.

Consider Alternatives

While the Superforecasters as a group assigned high odds for a Democratic sweep, individual Superforecasters predicted a variety of outcomes. A diversity of views is essential for good forecasting, but on issues you hold dear, considering other views is easier said than done. Over the week before the election, Good Judgment asked the Superforecasters as a group to imagine they could time-travel to a future in which the Republicans retained both the White House and the Senate. Regardless of their individual forecasts, they were then asked to explain why a “Blue Wave” election failed to occur in such a future.

This is called a pre-mortem, or “what if,” exercise. Thinking through alternative scenarios ahead of the actual outcome accomplishes several goals. It forces the forecaster to consider other perspectives, to rethink the reasoning and evidence supporting their forecasts. It also tests the forecaster’s level of confidence (over-confidence being a far more common issue than under-confidence) and helps avoid hindsight bias when evaluating the forecasts later.

Because Superforecasters already weigh multiple alternatives in making forecasts, this pre-mortem produced little change in the overall forecasts. Even after several days of internal debate on the “what if” scenarios, their aggregate probabilities barely moved.

But the exercise was useful. It showed that the Superforecasters’ predictions were well calibrated. It also produced multiple scenarios with detailed commentary, some of which proved clear-eyed in light of the actual events following the election.

Kjirste Morrell, one of Good Judgment’s leading Superforecasters, was among the participants in the exercise. She says she didn’t make large changes to her forecasts but underscores the value of the discussion.

“In retrospect, I should have placed more credence on the possibility of violence after the election, which was mentioned during the pre-mortem exercise,” she says.

Keep It Civil

A wise crowd encompasses diverse views. Studies based on the Good Judgment Project (GJP) found that being an “actively open-minded thinker” is positively correlated with being an accurate forecaster. That’s no mystery. Exposure to views with which we disagree can inform our understanding of the world. But Superforecasters don’t simply agree with everything. They know how to “disagree without being disagreeable.”

All forecasters can master this trait, as witnessed on our public forecasting platform, GJ Open. Throughout the 2020 election cycle, moderators observed very few comments that fell outside the reasonable bounds of civil discourse. This relative civility on GJ Open may surprise those accustomed to the rough-and-tumble of the Twitterverse. But it comes as no shock to Good Judgment’s co-founder Barb Mellers, whose research suggests that forecasting tournaments can reduce political polarization.

As the election cycle intensified and the public debate grew more heated and personal elsewhere on social media, GJ Open continued to emphasize facts and reasoned argument. It showed that forecasters can learn to remain focused on what matters to the accuracy of their predictions and block out the noise of inflammatory rhetoric.

Keep Score

Keeping score is essential to good forecasting, says Good Judgment’s co-founder Philip E. Tetlock. Superforecasters are not the only professionals who recognize this. Weather forecasters, bridge players, and internal auditors all know that tracking prediction outcomes and getting timely feedback are strategies that improve­­ forecasting performance. Superforecasters use quantifiable probabilities to express their forecasts and Brier scores to measure accuracy. Keeping score enables forecasters and companies to learn from past mistakes and to calibrate their forecasts in the future.

No single forecast is truly right or wrong unless it is expressed in terms of absolute certainty (0% or 100%). If the probability of President Trump being re-elected were 13% (Good Judgment’s forecast as of 1 November), he would win the election 13 out of 100 times if we could re-run history repeatedly. That’s why forecasting accuracy is best judged over large numbers of questions.

The Superforecasters’ accuracy has been scrutinized over hundreds and hundreds of questions, and a forecasting method that can beat them consistently has yet to be found. The Superforecasters know what they know—and what they don’t know. They know how to think through alternative scenarios and how to “disagree without being disagreeable.” They also know the importance of keeping score. When it comes to calculating the odds for even highly polarized topics, their process shows how best practices deliver the best accuracy.

* This article originally appeared in Luckbox Magazine and is shared with their permission.