Machine Learning Academy · 1 / 5

Choose what you want to predict

Predict a numeric quantity from information available before the job completes.

YOUR TASK

Make this happen

2 steps

Build the job-quantity XGBoost REGRESSION model targeting quantity, with priority as its feature.
Check the complete solution, then inspect any unmet requirements.

THE IDEA BEHIND IT

What this step adds

Build the job-quantity XGBoost REGRESSION model targeting quantity, with priority as its feature.

Files to work in

model.cococo. Other files are the working baseline. New files include named resource skeletons and TODO guidance. Complete their fields and connect them using the objectives, schema completion and reference guide.

Target versus feature

The target is the answer learned from historical rows. A feature is information available at prediction time. Including quantity as its own feature would leak the answer.

What this teaches

This small model is a configuration exercise, not evidence that priority predicts quantity well. Later evaluation must compare held-out predictions with a simple baseline.

Checks validate native model configuration and lesson requirements. They do not run SQL, normalize rows, train a model, score predictions or establish predictive quality.

Files to change: model.cococo

What you’re building: Author a reviewable job-quantity regression model with explicit features, missing-value handling and deliberate publication.

Read the starter files

main.cococo

ml_model_document "main" {
  format = "1"
  name = "job-quantity"
  backend = "xgboost"
  spec = {
    tabular = ml_model_tabular.quantity
  }
}

model.cococo

ml_model_tabular "quantity" {
  task = "REGRESSION"
  # TODO: add targetColumn — see the task above.
  # TODO: add featureColumns — see the task above.
}

features.cococo

ml_model_feature "priority" {
  column = "priority"
}

Supplied supporting files

Reference: machine-learning · authoring