User Guides

Prediction Guide

Use trained jobs for manual and batch prediction.

Quickstart
Get from sign-in to a completed first job.
Choosing a Service
Match your data and goal to the right workflow.
Data Preparation
Prepare tabular datasets and media manifests for successful uploads.
Jobs and Results
Understand statuses, reports, SHAP, and outputs.
Billing and Credits
How charges, estimates, and refunds work.
Prediction Guide
Use trained jobs for manual and batch prediction.
Troubleshooting
Resolve common user-facing errors quickly.
FAQ
Short answers to the most common platform questions.
Reference
Handbook and Technical Reference

Open the handbook for the full product guide, then use the model-method appendix when you need mathematical details.

Open Handbook Open model-method appendix

Prediction Guide

Prediction modes

  • Single-record/manual prediction: free for quick previews from a completed job.
  • Batch prediction: may be charged after the included row/item allowance, using uploaded row/item count, upload or media size, service multipliers, and selected model-family factors.

Before you predict

  • Use a completed job
  • Confirm the trained model is available
  • Match the training schema as closely as possible

Batch prediction tips

  • Reuse the same feature columns used during training
  • Keep column names aligned with the trained schema
  • Avoid extra unexpected columns unless the workflow explicitly supports them
  • Review the batch billing note before launch; small batches within the allowance can estimate to zero, while larger or media-heavy batches can reserve credits.

Common failure reasons

  • The best model artifact did not save correctly
  • The schema does not match training
  • Preprocessing artifacts are missing
  • The selected model format differs from what the loader expects

Related guides

  • Jobs and Results
  • Troubleshooting