The Wisdom and Madness of Crowds: Market Prices as Political Predictors!

    In this, the first full week in November 2024, the big news stories of this week are political, as the US presidential election reached its climactic moment on Tuesday, but I don’t write about politics, not because I do not have political views, but because I reserve those views are for my friends and family. The focus of my writing has always been on markets and companies, more micro than macro, and I am sure that you will find my spouting off about who I voted for, and why, off-putting, much as I did in his cycle, when celebrities and sports stars told me their voting plans. This post, though, does have a political angle, albeit with a market twist. During the just-concluded presidential election, we saw  election markets, allowing you to predict almost every subset of the election, not only open up and grow, but also insert themselves into the political discourse. I would like to use this post to examine how these markets did during the lead in to the election, and then expand the discussion to a more general one of what markets do well, what they do badly, i.e., revisit an age-old divide between those who believe in the wisdom of crowds and and those that point to their madness.

Election Forecasts: From polls to political markets

    I watched the movie “Conclave”just a couple of days ago, and it is about the death of a pope, and the meeting to pick a replacement. (It is based on a book by Robert Harris, one of my favorite authors.) In the movie, as the hundred-plus Catholic cardinals gathered in the Sistine chapel, to pick a pope,  I was struck by how the leading candidates gauged support and jockeyed ahead of the election, essentially informally polling their brethren. I know that the movie (and book) is fiction, but I am sure that the actual conclaves that have characterized papal succession for centuries have used  informal polling as a way of forecasting election winners for centuries. In fact, going back to the very first democracies in Greek and Roman times, where notwithstanding the restrictions on who could vote, there were attempts to assess election winners and losers, ahead of the event. 

    The first reported example of formal polling occurred ahead of the 1824 presidential election, when the Raleigh Star and North Carolina Gazette polled 504 voters to determine (rightly) that Andrew Jackson would beat John Quincy Adams. Starting in 1916, The Literary Digest started a political survey, asking its readers, and after correctly predicting the next four elections, failed badly in 1936 (predicting that Alf Landon would beat FDR in the election that year, when, in fact, he lost in a landslide). While polling found its statistical roots after that, it had one of its early dark moments, in 1948, when pollsters predictions that Thomas Dewey would beat Harry Truman were upended on Election Day, leading to one of the most famous headlines of all time (in the Chicago Tribune). In the decades after, polling did learn valuable lessons about sampling bias and with an assist from technological advancements, and the number of pollsters has proliferated. Coming into this century, pollsters were convinced that they had largely ironed out their big problems, but even at it peak, polls came with noise (standard errors), though pollsters were not always transparent about it, and the public took polling estimates as facts. 

    The fact that individual polls, even if not biased, are noisy (with ranges around estimates) led to a  poll aggregators, which collected individual polls and averaged them out to yield presumably a more precise estimate. Here, for example, is the aggregated value from Real Clear Politics (RCP), which has been doing this for at least four presidential election cycles now, leading into election days in the US (November 5):

    The pushback in poll-based forecasting (whether individual or aggregated) is that it may miss fundamentals on voter history and predilections, and in the last three cycles, there have been a few polling pundits who have used polling aggregates and their presumably deeper understanding of fundamentals to make judgments on who will win the election. Two are the best known are 538.com, a site that used to be part of the New York Times but is now owned by ABC, and Nate Silver’s personal assessment, and leading into the election, here were their assessments for the election:

Both arrive at their estimates using Monte Carlo simulations, based upon data fed into the system. Note that polls, aggregated polls and poll judgment calls have run into problems in the last decade, some of which may be insurmountable. The first is the advent of smartphones (replacing land lines) and call screening allows callers to not answer some call, and polls have had to struggle with the consequences for sampling bias. The second is that a segment of the population has become tough, if not impossible, to poll, sometimes lying to pollsters, and to the extent that they are more likely to be for one side of the political divide, there will be systematic error in polls that will not average out, and those errors feed into polling judgments.

    With poll-based forecasts being less reliable and trusted, a vacuum opened up leading into the 2024 elections, and political markets have stepped into the gap. While it has always been possible to bet on elections, either in Las Vegas or through UK-based betting sites like Betfair, they are odd-driven, opaque and restricted. In contrast, Polymarket opened markets on US election outcomes (president, senate, by state, etc.), and through much of 2024, it has given watchers a measure of what investors in that market thought about who would win the election. In the graph below, you can see the Polymarket prices for a “Trump win” and a “Harris win” in the months leading into the election:

In theory, this looks like an arbitrage opportunity, where you could buy the Trump win on the cheaper market and sell it on the more expensive one, but the transactions costs (1-2% in both markets) would have made them tough to pull off. 

The Wisdom of Crowds

    That trust in crowd judgments in guiding our actions is not restricted to politics. In an earlier part of this post, I talked about going to the movies, and it is indicative of the times we live in that my movie choice was made, not by reading movie reviews on the newspaper, but by movie ratings on Rotten Tomatoes. Once the movie was done, the restaurant choice I made was determined by Yelp reviews, and without boring you further, you can see this pattern unfold as you think about how you choose the products you buy on Amazon or even the services (plumbing, electrical, landscaping) that you go with, as a consumer. On a less personal and larger scale,  the block chains that underlie Bitcoin transactions represent a crowd sourcing of the checking process (performed by institutions like banks conventionally), and you can argue that trusting social media to deliver you information is essentially crowd-sourcing your news.

   With these examples, you can see one of the dangers of crowd judgments, and that is that in all the crowds described above (Rotten Tomatoes, Yelp, Amazon product reviews and social media), there is no cost to entry, or to offer an opinion, and that can dilute the power of the judgments. In every one of these sites, you can game the system to give high ratings to awful movies and terrible restaurants, and social media news can be filled with distortions. With markets, we introduce an entry fee to those who want to join the crowd in the form of price, and demand more money to amplify those views.  In the words of Nassim Taleb, opinionated people with no skin in the game can make outlandish predictions, often with no accountability. If you don’t believe me, watch the parade of experts and market gurus on any financial television channel, and notice how they are allowed to conveniently gloss over their own forecasts and predictions from earlier periods. In contrast, no matter what you think about the experience or motivations of traders on a market, they have to put money behind their views.

    When you use the price in a market as an assessment of the likelihood of an event, which is what you are implicitly doing when you trust Polymarket or Kashi prices as predictors of election winners, you are, in effect, trusting the crowd (albeit a selective one of those who trade on these markets) to be closer to the right outcome than polling experts or opinion leaders. When market price based forecasts are offered as alternatives to expert forecasts, the push back that you get is that experts have a deeper knowledge of what is being predicted. So, why do we trust and attach weight to the prices that investors assess for something? There are three reasons:

1. Information aggregation: One of the almost magical aspects of well-functioning markets is how pieces of information possessed by individual traders about whatever is being traded get aggregated, delivering a composite price that is effectively a reflection of all of the information. 
2. Real time adjustments to news: While experts (rightfully) take their time to absorb new information and reflect that information in their assessments, markets do not have the luxury of waiting. Consequently, markets react in real time, often in the moment, to events as they unfold, and studies that look at that reaction find that they often not only beat experts to the punch but deliver better assessments. 
3. Law of large numbers: It is true that individual traders in a markets can make mistakes, often big ones, in their assessments of value, and can sometimes also let their preconceptions and biases drive their trading. To the extent that these mistakes and biases can lie on both sides, they will average out, allowing the “right’ price to emerge from several wrong judgments.

There is also a strand of research that is developing on the forecasting abilities of experts versus amateurs and it is not favorable for the former. Phil Tetlock, co-author of the book on super forecasting, chronicles the dismal record of expert forecasts, and argues that the best forecasts come from foxes (knows many things, but not in depth) and not hedgehogs (with deep expertise in the discipline). To the extent that a market is filled with amateurs, with very different knowledge and skill sets, Tetlock’s work can be viewed as being supportive of market-based forecasts.

The Madness of Crowds

     Well before we had Rotten Tomatoes and Twitter were conceived, we had financial markets, and not surprisingly, much of the most interesting research on crowd behavior has come from looking at those markets.. Our experience there is that while markets allow for information aggregation and consensus judgments that are almost magical in their timeliness and assessment quality, they are also capable of making mistakes, sometimes monumental ones. One of my favorite books is Extraordinary Popular Delusions and the Madness of Markets, published in 1841, and it chronicles how market mistakes form and grow, using the South Sea Bubble and the Tulip Bulb Craze as illustrative examples. To those who believe that markets have somehow evolved since then to avoid these mistakes, behavioral finance provides the counter, which is that the behavioral quirks that gave rise to those bubble are still present, and may actually be amplified by technology and large platforms. The falsehood that was born in a pub in the South Sea bubble often looks weeks to work its way into market prices, but the same falsehood on a large social media platform today could affect prices almost instantaneously. 

    Without making this a treatise on behavioral finance, here are some of the problems that can lead markets off course, and make prices poor predictors of outcomes:    

1. Noise drowns out information: In finance, we use noise as a term to capture all of the stories and influences that should have no effect on value, but that can still affect prices. While noise exists in even the best-functioning markets, there is enough information in those markets to offset the noise effect, and bring prices back into sync with value. However, if noise is the dominant force in a market, it can drown out information, causing prices to delink from information. 
2. Momentum versus Fundamentals: On a related note, it is worth remembering that the strongest force in markets is momentum, where price movements are driven more by price movements in past periods, than by fundamentals. While in a well-functioning market, that momentum will  be checked by bargain hunters (if the price is pushed too low) or short sellers (if it is pushed too high), a market where one or the other of these players is either rare or non-existent can see momentum run rampant. It is one reason that I think that markets that restrict short selling, often labeling it as speculation, are creating the condition for market madness.
3. Participant bias: While markets require skin in the game from traders, that requires money, and that biases markets against people with little or no money. In political markets, for instance, it could be argued that the traders on Polymarket and Kalshi represent a subset of the population (younger, better off) that may differ from the voting population. 
4. Market Manipulation: The history of financial markets also includes clear cases where markets have been manipulated, to deliver profits to the manipulators. That problem becomes worse in markets with limited liquidity, where big trades can move prices, and where market insiders have access to data that outsiders do not. 
5. Illiquidity: All of the problems listed above become greater in a market where liquidity is light, since a large trade, whether motivated by noise, momentum or manipulation, will move prices more. 
6. Feedback loop: There are times where market prices can affect the fundamentals, and through them, the value of what is being traded. With publicly traded companies, a higher stock price, for instance, may allow the companies to issue shares at these higher prices, to finance investments and acquisitions. With the political markets, this feedback loop manifested itself in my social media feeds, where I often saw the Polymarket or Kashi charts being used by candidates to convince potential voters that they were winning (to get them to jump on the bandwagon) or losing (to get people to give them money).

To “crowd” or not to “crowd”

    I am convinced that in making our choices as consumers and citizens, we will be facing the choice between market-based assessments and expert assessment on more and more dimensions of our life. Thus, our weather forecasts may no longer come from meteorologists, but from a weather market where weather traders will tell us what tomorrow’s temperature will be or how much snow will be delivered by a snow storm. As we face these choices, there will be two camps about whether market prices should be trusted. One, rooted in the wisdom of markets, will push us to accept more crowd-sourcing and crowd-judgments, and the other, building on market madness, will point to all the things that markets can get wrong. 

    While I do believe that, in balance, the wisdom will offset the madness in most markets, there are places where I will stay wary, as a user of market prices. Put simply, rather than view this as an either/or choice, consider using both a  market pricing, if available, and a professional assessment. In the context of my discipline, which is valuation, I use both market assessment of country default risk, in the form of sovereign CDS spreads, and sovereign ratings, from the ratings agencies. The latter have more knowledge and expertise, but they are also slow to react to changes on the ground, and I am glad that I have market prices to fill in that gap.  If you are planning to trade on these markets, I would hope you will heed my admonition from this post, where I argued that if you are buying or selling something that has no cash flows, you can only trade, not value, it. In the context of political markets, the price that you are paying is a function of probabilities of outcomes and your capacity to make money in the market will come from you being able to assess those probabilities better than the rest of the market. 

    There is another use for these political market securities that you may want to consider. To the extent that you feel emotionally invested in one candidate winning, and you don’t have much faith in your probability assessments, you may want to consider buying shares in the other candidate. That way, no matter what the outcome, you will have a partially offsetting benefit; a win for your candidate will make you happy, but you will lose some money on your political market bet, and a loss for your candidate may be emotionally devastating, but you may be able to soothe your pain with a financial windfall.

YouTube Video

Political Market Links

1. Polymarket
2. Kalshi