Difference between Binary Prediction and True Exposure, with Implications for Forecasting Tournaments and Prediction Markets: TalebVW Staff
Binary prediction: There are serious differences between predictions, bets, and exposures that have a yes/no type of payoff, the “binaries”, and those that have varying payoffs, which we call the “vanilla”. Real world exposures tend to belong to the vanilla category, and are poorly captured by binaries. Vanilla exposures are sensitive to Black Swan effects, model errors, and prediction problems, while the binaries are largely immune to them. The binaries are mathematically tractable, while the vanilla are much less so. Hedging vanilla exposures with binary bets can be disastrous–and because of the human tendency to engage in attribute substitution when confronted by difficult questions, decision-makers and researchers often confuse the vanilla for the binary.
Binary Predictions vs Vanilla Predictions
Binary: Binary predictions are about well defined discrete events, such as whether a person will win the election, a single individual will die, a team will win a contest. We call them binary because the outcome is either 0 (the event does not take place) or 1 (the event took place). You cannot have five hundred people winning a presidential election.
Vanilla: “Vanilla” predictions, also known as natural exposures, correspond to situations in which the payoff is continuous and can take several values. The “vanilla” designation comes from option exposures that are open-ended as opposed to the binary ones that are called “exotic”. The designation “vanilla” is fitting outside option trading because the exposures they designate are naturally occurring continuous variables, as opposed to the binary that which tend to involve abrupt institution-mandated discontinuities. The vanilla add a layer of complication: profits for companies or deaths due to terrorism or war can take many, many potential values. You can predict the company will be “profitable”, but the profit could be $1 or 10 billion.
Most of the variables affecting the vanilla are not bounded, or have a remote boundary. So the prediction of the vanilla is marred by Black Swan effects. A few prescient observers saw the potential for war among the Great Power of Europe in the early 20th century but virtually everyone missed the second dimension: that the war would wind up killing an unprecedented twenty million persons, setting the stage for both Soviet communism and German fascism and a war that would claim an additional 60 million, followed by a nuclear arms race from 1945 to the present, which might some day claim 600 million lives.
Binary predictions via