The Market Conditions chip on the Fear & Greed forecast is a 3-state Markov-switching model. It assumes the index is always in one of three hidden moods — fear, neutral or greed — each with its own typical drift and volatility, plus a probability of jumping from one mood to another.
A single mean-reverting model (like the OU baseline) treats a calm market and a panic with the same math. But sentiment plainly behaves differently inside a crash than inside a melt-up: jumpier and more volatile in fear, calmer and stickier in greed. The Market Conditions model captures that by letting each state carry its own drift and volatility, and by estimating how likely the index is to stay put or switch. The forecast then blends the states by how probable each one is right now.
Flexibility isn't free. Three states mean more quantities to estimate from a limited sentiment history, which raises the risk of reading patterns into noise. Whether that flexibility pays off on current data is exactly what the "Model performance" table under the Fear & Greed forecast is for: it shows the Market Conditions model's coverage, MAPE, RMSE, Brier and hit-rate next to the simpler baselines so you can see whether the extra states earn their complexity.
Fear, neutral and greed. The model treats these as hidden moods the index switches between, each with its own typical drift and volatility, and estimates how likely it is to stay in one or jump to another.
Because sentiment behaves differently inside a panic than inside a melt-up — jumpier in fear, stickier in greed. One fixed equation can't express that; three states with their own dynamics can.
More states mean more quantities to estimate from limited history, so there's a higher risk of fitting noise. Check the 'Model performance' table under the chart to see whether the Market Conditions model actually beats the simpler baselines on current data.
Browse all S&P 500 tickers to see this metric applied to individual companies.
Educational research only — not investment advice.