# Prediction The Prediction tool uses a [Digital Twin](/more-details/digital-twin.md) — RootCause's runnable causal model of your business — and an input scenario to return the most likely value of a target variable with a confidence interval. For the workflow that produces a Digital Twin in the first place, see [Step 6: Run Simulations](/user-guide/simulations.md). *** ## Why a Digital Twin prediction beats an LLM prediction A prediction from a Digital Twin gives you three things an LLM cannot. 1. **Repeatable.** The same input always produces the same output. 2. **Explainable.** The prediction comes from a DAG — a system of intertwined equations whose causal logic can be inspected end-to-end. If A causes B, B causes C, and C, D, and E together cause F, you can read the chain. 3. **Calibrated.** Every prediction comes with a known confidence interval and an understood distribution of outcomes. A single Prediction looks like this.
A Churn prediction with No: 94.4% ± 12.3% and Yes: 5.6% ± 5.6%

One row of a Prediction output: the predicted class, the confidence, and the alternative outcome distribution.

*** ## Starting a simulation Open a Digital Twin from the Digital Twin Management page. The right-hand panel shows the Overview by default; click **Simulations**, then **+ New Simulation**. This opens the [type picker](/more-details/digital-twin/summary_of_digital_twin_simulations.md) — choose **Prediction**.
The Simulations panel inside a Digital Twin, showing recent simulations and suggested ones

The Simulations panel inside a Digital Twin. Recent runs appear at the top; the model also generates suggested simulations.

*** ## Step 1: Choose target variables Target variables are the outcomes you want to predict. Selecting a target removes it from the input table on the next step — you supply its drivers, not the target itself.
Step 1 of the Prediction setup: choose target variables, with Churn selected

One target is enough; multiple targets run in the same simulation.

*** ## Step 2: Provide input records Each row is one scenario. RootCause filters the columns to variables with a causal path to the target. The form starts empty. Required fields are highlighted; you cannot run the simulation until they are filled.
The full Prediction setup form, empty, with validation errors at the bottom

The full setup form, empty. Highlighted fields are mandatory.

Numeric fields take values directly; categorical fields offer dropdowns. Pick `` for any field you don't have a value for.
The same form with one row filled in across all input fields

One scenario filled in. Add more rows to predict multiple cases in a single run.

The tabs above the form offer three other input methods: * **File Upload** — a CSV or Parquet file with one row per scenario. * **Data View** — pull rows directly from a saved Data View. * **Field Input** *(default)* — the form view shown above. *** ## Step 3: Confidence level The default of 0.95 means the model is 95% confident the actual value falls within the shown range. Higher confidence widens the interval; lower narrows it. Leave the default unless you have a specific reason to change it. *** ## Reading the result Clicking **Run Simulation** opens the result page, with the configuration summary, an AI summary of the prediction, and the predictions table.
A completed Prediction run showing the run info, configuration summary, AI summary, and predictions table

A completed Prediction run. The predictions table at the bottom is the core artefact.

The full output is one shareable record of the prediction.
The full Prediction run page scrolled end to end

The full run page. Each section — AI summary, predictions table, segment breakdowns — exports as PDF.

The predictions table shows each input scenario, the predicted class or value, and the confidence interval — the artefact a Digital Twin produces and an LLM cannot. *** ## Past simulations The Simulations panel lists recent runs. For the full history, click **View All** at the top right.
The Simulations panel with the View All link highlighted

View All opens every simulation ever run against this twin, including failed ones.

The history page lists every run with type, status, and creation date.
The simulation history page listing past runs against this Digital Twin

Simulation history. Click any row to reopen the result.

*** ## Other Simulation Types * [Intervention](/more-details/digital-twin/summary_of_digital_twin_simulations/intervention.md) — measure the effect of changing a variable. * **Optimization** *(coming soon)* — find the input combination that maximises or minimises a target. See [Step 6: Run Simulations](/user-guide/simulations.md) — general overview. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.rootcause.ai/more-details/digital-twin/summary_of_digital_twin_simulations/prediction.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.