The Q-PI chip — short for quantum path-integral — forecasts Fear & Greed by sampling many possible future paths and weighing them into a full probability distribution. The key ingredient is a potential landscape built from the index's own history (formally, the negative log of the historical distribution, V(x) = −log ρ(x)): valleys where the index likes to sit, hills it rarely crosses.
Most models produce a single averaged path — a middle that may satisfy no one. Because the Q-PI landscape can have more than one valley, its forecast can be bimodal: 'either sentiment stays greedy, or it drops to fear', with a probability on each branch, rather than splitting the difference. That is a more honest picture when the market genuinely faces a fork in the road. The idea shares its mathematical roots with the Feynman path integral and the Schrödinger equation used in Quantustik's price forecasts.
This is an output-level explainer: it describes what the Q-PI model assumes and what its forecast looks like, not the sampler internals. Whether Q-PI actually forecasts better than the simpler baselines is not something to take on trust — the "Model performance" table under the Fear & Greed forecast re-runs the walk-forward backtest and reports its coverage, MAPE, RMSE, Brier and directional hit-rate beside every other model.
It borrows the physics idea of summing over all possible paths rather than predicting one. The model samples many candidate future sentiment paths through a landscape built from history and weighs them into a full probability distribution.
Because the landscape can have more than one valley. When the market faces a genuine fork, the forecast can be bimodal — 'stays greedy or drops to fear' with a probability on each — instead of an averaged middle that fits neither.
Check the 'Model performance' table under the Fear & Greed forecast — it re-runs the walk-forward backtest on current data and shows Q-PI's coverage, MAPE, RMSE, Brier and hit-rate next to every baseline so you can compare them yourself.
Browse all S&P 500 tickers to see this metric applied to individual companies.
Educational research only — not investment advice.