Model card

astris-cohort-kmeans-v1

K-means cohort segmenter (Lloyd iteration with k-means++ seeding) that groups candidates by their support-feature vector to give caseworkers workable cohorts. Descriptive segmentation only — it never scores an individual for matching and is not a retention voter.

At a glance

Kindclustering kmeans
Version1.0.0
StatusActive — contributing to scores
Ensemble weight0
Trained atNot trained yet
Trained onn/a
ArtifactNo artifact (heuristic or pre-training)

Metrics

{
  "role": "descriptive_segmentation",
  "algorithm": "lloyd_kmeanspp",
  "validation": "synthetic_seed",
  "real_cohort": "pending"
}

Notes

Caseworker cohort discovery surface; does not score people and does not vote on retention — weight 0. See api/ml/kmeans.py.