Regression & Modeling · TOOL GUIDE

Predict From Model

Open Quantly ↗

Understand the method. Use it with confidence.

Predict a value or class from a previously fitted model artifact. Quantly runs the method against your active analysis context and returns structured results for review and interpretation.

01

When to use it

Use this tool to quantify relationships, explain variation, or predict an outcome from one or more features.
Use it only when the selected variables and study design match the method's requirements.

02

How to use it

  1. Open the tool from the Quantly Tools panel.
  2. Confirm the active dataset and analysis session.
  3. Set Analysis Result ID (Optional): Optional prior analysis result ID. If omitted, the latest predictive model in the active session is used.
  4. Set Input Values JSON (Required): JSON object containing feature names and values for the prediction.
  5. Set Confidence Level (Optional): Confidence level for the prediction interval, between 0 and 1.
  6. Set Prediction Horizon (Optional): Required for saved Cox models. Enter the time horizon at which survival should be estimated.
  7. Review optional or advanced settings and keep defaults unless your design requires a change.
  8. Run the tool, inspect warnings and diagnostics, then save or export the result with its assumptions.
03

How to interpret results

Review coefficients or feature effects, uncertainty, validation metrics, residual diagnostics, and leakage risk. Association is not causation, and performance should be evaluated on data not used for fitting.