Prophesee Foresight

Know what happens next.

Predictive intelligence as an operating capability. Point Foresight at your data and it profiles what is predictable, builds the models itself, proves them blind, and keeps them honest every day. Ingest. Predict. Prove.

Model league: invoice late-payment
Backtested · calibrated
ModelScore
Ensemble CHAMPION94.1
LightGBM93.2
XGBoost92.8
CatBoost91.5
Prophet88.9
Baseline (naive)71.0
Calibration
Predicted vs. observed. The champion tracks the reference line · the odds it quotes are the odds you get.
62 models competing · 11 champions live · 38,000 predictions scored
See it working

The model workspace

The league, the calibration curve, the challenger in waiting and the blind backtest, on one screen.

See it on your data →
The catalogue

Ask five kinds of question

Every new question used to mean a new project, scoped from nothing and stale on arrival. Five kinds of question cover most of what a business asks its data, and the catalogue already holds the model families for each. You bring the question. The catalogue brings the field.

  • 62 models across 13 families, competing for every question.
  • How many, which ones, how risky, when, and why.
  • Forecasting, classification, anomaly scoring, survival timing, causal drivers.
  • A model for each question you ask, not one model picked early.
The five question types Foresight answers: how many, which ones, how risky, when and why, across 62 models in 13 families
How it works

Run one continuous loop

Run machine learning as a project and each model is a small consulting engagement: months to build, stale on arrival, dead before production. One pipeline runs the whole lifecycle instead, with a validation gate at every step. Nineteen specialist agents, one governed pipeline, zero data-science backlog.

  • Quality, no leakage, held-out and calibrated: the gates cannot be skipped.
  • Retraining runs on schedule and on drift, inside thresholds you set.
  • Every decision the platform takes is logged and reversible.
  • Every scored prediction sharpens the next selection.
The Foresight pipeline: profile, frame, compete, serve, prove and learn, with what it proves feeding back into how it frames

The gates: quality, no leakage, held-out, calibrated

Prove

Tell a real result from luck

A good-looking backtest is easy to produce and easy to believe. So Foresight runs twenty backtests, and nineteen of them run on history with nothing in it to find. If you cannot pick out the real one, neither could anybody else, and the result was luck.

  • One of these is a real model on real history.
  • Nineteen learned nothing, because there was nothing to learn.
  • Nothing reaches production untested.
  • Every model that goes live carries its backtest with it, misses included.
Twenty backtests side by side, nineteen run on history with nothing in it to find and one real result
Watch

Retire a model before it goes quietly wrong

A model left alone is quietly wrong. Behaviour changes, accuracy slips, and nobody re-checks the slide that got it approved. Foresight scores every champion daily against what actually happened, trains challengers alongside it, and promotes the challenger when it wins on live data.

  • January: a champion ships, calibration published, on the record.
  • April: behaviour changes and the daily score sees it first.
  • June: the challenger overtakes on live data and is promoted, with approval.
  • December: the year closes at the accuracy the catalogue published.
The standard it must holdPROMOTED . WITH APPROVALACCJANAPRJUNDECThe old championThe challenger
Accuracy, daily. No model was left alone.
Yours

Open either door to the same engine

A business user should not have to learn hyper-parameters, and a data scientist should not have to give them up. The same catalogue sits behind both doors: a wizard for the business user, a workbench for the data scientist. Nobody has to become a data scientist. Nobody has to stop being one.

  • Auto Mode asks what you want to predict and over what horizon.
  • Expert Mode opens the catalogue, the sandbox and the controls.
  • Honesty about the data: viable, more history needed, or not yet.
  • Promote goes to approval, not straight to production.
AUTO MODE
For the business user
What do you want to predict?
  • Invoice paid latePREDICTABLE
  • Order arrives latePREDICTABLE
  • Finding breaches deadlineMORE HISTORY
7 days30 days90 days
Deploy: scorecard first, then live
EXPERT MODE
For the data scientist
Blend of the top three
  • LightGBM93.2
  • CatBoost91.5
  • Random forest90.4
Hyper-parametersValidationFeatures
Promote: goes to approval, not to production
One decision layer

Runs with the other engines

A prediction is built once, proved once and governed once. Horizon takes the delivery probabilities, Pulse takes the anomaly and predictive alert scores, Nexus takes the behavioural ranking. Nothing is modelled twice.

Questions about Foresight

Ingest. Predict. Prove.

Predictive intelligence turns hindsight into foresight. See it run on your data.