By James Pethokoukis

It has begun. Not just a mere Federal Reserve tightening cycle. That actually began in March when the US central bank raised interest rates for the first time since 2018. But with a rare half-percentage-point interest rate increase — the largest since 2000 — (along with a plan to shrink its $9 trillion asset portfolio), the Fed has embarked upon, The Wall Street Journal reports, “the most aggressive Fed tightening of monetary policy at one meeting in decades, aimed at rapidly reducing the economic stimulus that has contributed to rising price pressures.” This from Goldman Sachs:

Chair Powell said that 50bp increases in the funds rate should be on the table at the next couple of meetings. We see this as a strong signal. We already expected a second 50bp hike in June and are revising our Fed forecast to include a third 50bp hike at the July meeting too (vs. 25bp previously).

And where will these Fed actions lead? Possibly to a recession. Some big Wall Street banks see a 30 percent or 40 percent chance of a downturn over the next year or two. And, of course, the economy just had a negative first quarter, although the consensus is that Q2 will be positive. One thing I’ve been paying attention to is Metaculus. One might call it a prediction market. But there’s more to it. More like AI meets the wisdom of crowds. As the site describes itself:

Metaculus is an online forecasting platform and aggregation engine that brings together a global reasoning community and keeps score for thousands of forecasters, delivering machine learning-optimized aggregate forecasts on topics of global importance. 

First, questions are carefully specified so that everyone understands beforehand and afterward which kinds of outcomes are included in the resolution, and which are not. Forecasters then give precise probabilities that measure their uncertainty about the outcome.

Second, Metaculus aggregates the forecasts into a simple median (community) prediction, and an advanced Metaculus Prediction. The Community Prediction is simple to calculate: it finds the value for which half of predictors predict a higher value, and half predict lower. Surprisingly, the Community Prediction is often better than any individual predictor! This principle is known as the wisdom of the crowd, and has been demonstrated on Metaculus and by other researchers. Intuitively it makes sense, as each individual has separate information and biases which in general balance each other out (provided the whole group is not biased in the same way).

Third, we measure the relative skill of each forecaster, using their quantified forecasts. When we know the outcome of the question, the question is “resolved”, and forecasters receive their scores. By tracking these scores from many forecasts on different topics over a long period of time, they become an increasingly better metric of how good a given forecaster is. We use this data for our Metaculus Prediction, which gives greater weight to predictions by forecasters with better track records. These scores also provide aspiring forecasters with important feedback on how they did and where they can improve.

Here are a few of the recession-related forecasts — which are unfortunately gloomier than Wall Street’s:

The post The Chances of a Recession Might Be Worse than You Think — Or at Least Worse than Wall Street Thinks appeared first on American Enterprise Institute – AEI.