Parallel model engine
ML Lab
Open anomalies
499
data contradicting peers or own record
Open connections
2,907
implied by the ontology, stated nowhere
Last scan
2026-07-29
weekly · Mondays 09:40 UTC · pg_cron
Learned models
2
score refresh weekly · retrain monthly
Engine runs
| Kind | Started | Finished | OK | Stats |
|---|---|---|---|---|
| anomaly_scan | 2026-07-29 | 2026-07-29 | yes | resolved=0 · penalty_spike=234 · staffing_cliff=127 · ownership_churn=0 · staffing_collapse=35 · high_risk_high_stars=103 |
| connection_scan | 2026-07-29 | 2026-07-29 | yes | resolved=0 · serial_acquirer=5 · cross_chain_owner=500 · enforcement_cluster=938 · fleet_risk_signature=1464 |
| retrain | 2026-08-01 | 2026-08-01 | FAILED | error=No module named 'numpy' |
| score_refresh | 2026-08-03 | 2026-08-03 | FAILED | error=permission denied for table cii_model_registry |
| model p_adverse_action_12m | 2026-07-29 | v0.1 | default | R23/W4-3. Deterministic logistic p(Medicare termination within 12m), SNF only. Label = first POS termination date (any code: voluntary closure, involuntary termination, merger exit); facilities already terminated by the panel date are excluded, not counted as safe. Trained on panels 2024-07/2024-10/2025-01 (n=46,466, 283 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.971, top-decile lift 9.5x, top-decile capture 95.4% of the 65 terminations that followed. Separability is high because closures announce themselves in the data: collapsing occupancy is the strongest signal, and the learned NEGATIVE weight on 12m deficiency counts is the surveys-stop signature of a facility winding down, not a claim that clean inspections are dangerous. Same 15 as-of-date features and anti-leakage chassis as p_chow_12m; SFF entry rejected as a label (only one month of SFF history exists, so as-of transitions cannot be reconstructed). Score = probability x 100; grade NULL. Not in any composite. |
| model p_chow_12m | 2026-07-29 | v0.1 | default | R22/W4-2. Deterministic logistic p(CHOW within 12m), SNF only. Trained on panels 2024-07/2024-10/2025-01 (n=50,700, 1,207 positives), evaluated on the held-out later panel 2025-04 BEFORE shipping: AUC 0.874, top-decile lift 5.0x (top 10% of predictions captured 49.6% of the CHOWs that actually closed in the next 12 months). Shipped coefficients are the evaluated ones; no post-holdout refit. Caveat: holdout positives (133) run below the training base rate because recent CHOWs surface in public records with a lag, so measured lift is conservative. Features are as-of-date public records: PBJ staffing level/trend/contract share (quarterly history to 2022Q1), deficiency and CMP counts (12m), ownership tenure and churn from CHOW-evidenced transactions, beds, occupancy, ownership type, chain size. Chain membership and ownership type are current-state (history not published). SFF and star ratings deliberately excluded (no as-of history). Notable learned direction: long ownership tenure RAISES sale odds and a recent prior CHOW lowers them. Score = probability x 100; grade is NULL because a probability is not a quality letter. Not in any composite. |
scans execute inside Postgres on pg_cron; score refreshes and retrains run in the API process, triggered over pg_net — the cadence survives sandbox loss
Anomalies — 0 open · Ownership churn
| Facility | Type | Signal | Setting | State | City | First seen |
|---|
two or more changes of ownership inside 24 months
Connections — 5 open · Serial acquirer
| Subject | Relation | Strength | Evidence | First seen |
|---|---|---|---|---|
| FANNIN COUNTY HOSPITAL AUTHORITY | Serial acquirer | 8 facilities / 24mo | 2026-07-29 | |
| NORTH BIG HORN HOSPITAL DISTRICT | Serial acquirer | 8 facilities / 24mo | 2026-07-29 | |
| FRIO HOSPITAL DISTRICT | Serial acquirer | 6 facilities / 24mo | 2026-07-29 | |
| WINNIE-STOWELL HOSPITAL DISTRICT | Serial acquirer | 6 facilities / 24mo | 2026-07-29 | |
| SWEENY HOSPITAL DISTRICT | Serial acquirer | 5 facilities / 24mo | 2026-07-29 |
one buyer organization taking over 5+ facilities inside 24 months — a chain being assembled in real time