Reads as: riskier than 45.8% of the 14,684 facilities in the snf peer group. percentile within peer group, 100 = highest risk. Grade bands are fixed percentile cuts (F is the top 5% of peer risk), so a grade is a position, not an absolute level.
weighted_contribution sums to pre_rank_index over rows where counts_toward_index is true. The composite is the facility's percentile position of that index within its peer group, so contributions explain the input, and the rank explains the score.
ML signals — parallel engine
2
Kind
Finding
Signal
Subject
First seen
connection
Owner spans multiple chains
15 chains
CIBC BANK USA
155 facilities
connection
Owner spans multiple chains
7 chains
RUBENSTEIN DAVID
31 facilities
Findings from the always-on scanning layer: anomalies on this facility, connections through its current owners and past buyers. Runs beside the deterministic composite, never inside it. Full board on the ML Lab page.
Change-of-ownership footprint in the CMS Provider of Services file: control-family, legal-name and address deltas across quarterly snapshots, plus certification reset recency and Medicare tenure.
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.
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.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later financial_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later regulatory_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Pre-registry model iteration, superseded by a later staffing_risk rebuild. Rows retained for audit per project convention (see regulatory_risk v0.4-pos); never consumed because v_cii_api_facility_score and the composite eligibility join both require status = default. Backfilled 2026-07-26 by alert triage on model_registry_integrity.
Rows with counts_toward_composite false come from models that are addressable or retracted rather than default. They exist and may be informative, but they did not enter the published composite and must not be summed as though they had.
p_adverse_action_12m: probability the facility's Medicare participation terminates within 12 months (any POS termination code; already-terminated facilities are excluded, not scored safe). Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.971, top-decile lift 9.5x. Closures announce themselves: collapsing occupancy dominates, and fewer recent surveys is a winding-down signature. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models. | p_chow_12m: probability of a change of ownership within 12 months. Deterministic logistic over as-of-date public records, SNF only. Holdout (2025-04 panel, evaluated before shipping): AUC 0.874, top-decile lift 5.0x. inputs.features holds raw feature values, inputs.contributions each feature's standardized pull on the log-odds. Predictions never enter the composite. See /v1/models for full notes.
Probability the facility's Medicare participation ends within 12 months, from public records only. Red bars raise exit odds. A negative pull from deficiencies is the winding-down signature — surveys stop as a facility empties — not evidence that clean inspections are dangerous.
Staffing vs peers
16
2025Q4 HPRD
This facility
KY median
National median
National p25–p75
Total nurse
3.09
3.11
3.28
2.90–3.77
RN
0.17
0.41
0.39
0.25–0.58
Weekend total
2.64
3.01
3.11
—
Weekday total
3.26
3.16
3.35
—
Quarter
Days
Avg census
Total HPRD
RN
LPN
CNA
Weekend
Contract %
2025Q4
92
86.8
3.09
0.17
0.96
1.96
2.64
0.0%
2025Q3
92
87.4
3.31
0.24
0.94
2.12
2.87
0.0%
2025Q2
91
89.4
3.29
0.28
0.95
2.07
2.85
0.0%
2025Q1
90
88.2
3.21
0.34
0.82
2.05
2.94
0.0%
2024Q4
92
85.5
3.32
0.35
0.81
2.15
3.11
0.0%
2024Q3
92
85.9
3.34
0.33
0.93
2.09
3.17
0.0%
2024Q2
91
86.2
3.29
0.29
0.81
2.18
3.12
0.0%
2024Q1
91
84.7
3.38
0.27
0.82
2.29
3.21
0.0%
2023Q4
92
82.9
3.42
0.27
0.86
2.29
3.18
0.0%
2023Q3
92
87.3
3.20
0.31
0.75
2.14
3.08
0.2%
2023Q2
91
88.7
3.29
0.34
0.70
2.24
3.17
14.2%
2023Q1
90
80.9
3.34
0.34
0.74
2.26
3.11
3.4%
2022Q4
92
84.8
1.99
0.30
0.60
1.09
2.16
12.3%
2022Q3
92
81.3
3.01
0.30
0.72
1.99
2.98
43.2%
2022Q2
91
74.0
3.25
0.27
0.85
2.14
3.11
40.2%
2022Q1
90
73.4
3.04
0.25
0.78
2.01
2.97
17.8%
HPRD is census-weighted: total hours over the quarter divided by total resident-days, not an average of daily ratios. Source is CMS Payroll-Based Journal daily records; only SNFs report PBJ, so other settings legitimately return zero rows.
Penalties
0
No penalties on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Deficiencies
1
D × 1
Survey
Type
Tag
Deficiency
Scope
Corrected
2024-06-06
Health · complaint
F0584
Honor the resident's right to a safe, clean, comfortable and homelike environment, including but not limited to receiving treatment and supports for daily living safely.
D
2024-07-02
scope_severity uses the CMS letter grid: A is least serious, L most. J, K and L are immediate jeopardy. Rows are the surveyor's findings of record, not the model's opinion.
Licensure actions
0
No licensure actions on record for this facility. Absence of a record here means the sources CII ingests contain none, not that none exists anywhere.
Ownership
33
Owner
Role
Pct
From
Status
Source
PLATSCHEK, ALEXANDER
5% OR GREATER INDIRECT OWNERSHIP INTEREST
24%
2024-05-24
current
pecos_ownership
RUBENSTEIN, DAVID
5% OR GREATER INDIRECT OWNERSHIP INTEREST
11%
2024-05-24
current
pecos_ownership
THE GOLDIE PLATSCHEK 2021 FAMILY TRUST
5% OR GREATER INDIRECT OWNERSHIP INTEREST
5%
2024-05-24
current
pecos_ownership
CIBC BANK USA
5% OR GREATER SECURITY INTEREST
—
2018-09-01
current
pecos_ownership
DICKENSON, BENITA
OPERATIONAL/MANAGERIAL CONTROL
—
2018-09-01
current
pecos_ownership
KELMAN, MOSHE
MANAGING CONTROL - GOVERNING BODY
—
2018-09-01
current
pecos_ownership
KENTUCKY HEALTH HOLDINGS, LLC
ADP OF THE SNF
—
2024-05-24
current
pecos_ownership
KENWOOD HEALTH CENTER HOLDCO, LLC
5% OR GREATER DIRECT OWNERSHIP INTEREST
—
2024-05-24
current
pecos_ownership
KY MAGNOLIA, LLC
ADP OF THE SNF
—
2026-01-23
current
pecos_ownership
KY MAGNOLIA, LLC
INDIRECT OWNERSHIP INTEREST
—
2024-05-24
current
pecos_ownership
METROPOLITAN COMMERCIAL BANK
5% OR GREATER SECURITY INTEREST
—
2018-09-01
current
pecos_ownership
PLATSCHEK, ALEXANDER
5% OR GREATER DIRECT OWNERSHIP INTEREST
—
2018-09-01
current
pecos_ownership
PLATSCHEK, GOLDIE
5% OR GREATER DIRECT OWNERSHIP INTEREST
—
2018-09-01
current
pecos_ownership
RUBENSTEIN, DAVID
5% OR GREATER DIRECT OWNERSHIP INTEREST
—
2018-09-01
current
pecos_ownership
RUBIWEB SERVICES GROUP USA, LLC
INDIRECT OWNERSHIP INTEREST
—
2024-05-24
current
pecos_ownership
SMITH, BETHANY
OPERATIONAL/MANAGERIAL CONTROL
—
2023-08-25
current
pecos_ownership
SPKY OPCO, LLC
INDIRECT OWNERSHIP INTEREST
—
2024-05-24
current
pecos_ownership
STOCKDALE, DANIEL
OPERATIONAL/MANAGERIAL CONTROL
—
2023-10-16
current
pecos_ownership
SUTHAR, MEHUL
OPERATIONAL/MANAGERIAL CONTROL
—
2018-09-01
current
pecos_ownership
GGKY OPCO, LLC
5% OR GREATER INDIRECT OWNERSHIP INTEREST
41%
2024-05-24
ended 2026-05-18
pecos_ownership
GOLDIE PLATSCHEK
5% OR GREATER INDIRECT OWNERSHIP INTEREST
41%
2024-05-24
ended 2026-05-18
pecos_ownership
BENITA DICKENSON
OPERATIONAL/MANAGERIAL CONTROL
33%
2018-09-01
ended 2026-05-18
pecos_ownership
GOLDIE PLATSCHEK
5% OR GREATER DIRECT OWNERSHIP INTEREST
25%
2018-09-01
ended 2026-05-18
pecos_ownership
ALEXANDER PLATSCHEK
5% OR GREATER INDIRECT OWNERSHIP INTEREST
24%
2024-05-24
ended 2026-05-18
pecos_ownership
ALEXANDER PLATSCHEK
5% OR GREATER DIRECT OWNERSHIP INTEREST
15%
2018-09-01
ended 2026-05-18
pecos_ownership
DAVID RUBENSTEIN
5% OR GREATER INDIRECT OWNERSHIP INTEREST
11%
2024-05-24
ended 2026-05-18
pecos_ownership
DAVID RUBENSTEIN
5% OR GREATER DIRECT OWNERSHIP INTEREST
7%
2018-09-01
ended 2026-05-18
pecos_ownership
MOSHE KELMAN
5% OR GREATER INDIRECT OWNERSHIP INTEREST
3%
2024-05-24
ended 2026-05-18
pecos_ownership
SAMZIL HOLDINGS LLC
5% OR GREATER INDIRECT OWNERSHIP INTEREST
3%
2024-05-24
ended 2026-05-18
pecos_ownership
BETHANY SMITH
OPERATIONAL/MANAGERIAL CONTROL
—
2023-08-25
ended 2026-05-18
pecos_ownership
DANIEL STOCKDALE
ADP OF THE SNF
—
2023-10-16
ended 2026-05-18
pecos_ownership
MEHUL SUTHAR
ADP OF THE SNF
—
2018-09-01
ended 2026-05-18
pecos_ownership
MOSHE KELMAN
MANAGING CONTROL - GOVERNING BODY
—
2018-09-01
ended 2026-05-18
pecos_ownership
PECOS ownership and managing-control associations. Current edges have no end date in the source; historical edges are retained.
Related-party costs
5
FY end
Total allowable
Rent
Home office
Therapy
Staffing
Counterparties
PropCo
2024-12-31
$2,062,259
$1,195,768
—
$389,092
—
0
—
2023-12-31
$1,380,352
$703,286
—
$440,603
—
0
—
2022-12-31
$1,246,436
$592,933
—
$446,800
—
0
—
2021-12-31
$1,373,091
$574,484
—
$616,582
—
0
—
2020-12-31
$1,393,598
$603,084
—
$630,726
—
0
—
Cost-report related-party spend by fiscal year. has_propco flags real-estate counterparties.
Most recent same-state, same-setting trades. Most CHOW-derived trades carry no disclosed consideration, so price, $/bed, and cap rate show only where a sale price was resolved from a deed or filing — blanks are honest, not missing data.
Market rent context
34
Geo
Kind
BR
Amount
As of
Source
county 21151
acs median gross
0
$714
2024-12-31
CENSUS_ACS5
county 21151
fmr
0
$666
2025-10-01
HUD_USER_FMR
county 21151
acs median gross
1
$735
2024-12-31
CENSUS_ACS5
county 21151
fmr
1
$785
2025-10-01
HUD_USER_FMR
county 21151
acs median gross
2
$882
2024-12-31
CENSUS_ACS5
county 21151
fmr
2
$904
2025-10-01
HUD_USER_FMR
county 21151
acs median gross
3
$1,063
2024-12-31
CENSUS_ACS5
county 21151
fmr
3
$1,257
2025-10-01
HUD_USER_FMR
county 21151
acs median gross
4
$1,344
2024-12-31
CENSUS_ACS5
county 21151
fmr
4
$1,416
2025-10-01
HUD_USER_FMR
county 21151
acs median gross
$889
2024-12-31
CENSUS_ACS5
county 21151
acs recent mover gross
$1,001
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
0
$712
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
1
$755
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
2
$906
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
3
$1,097
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
4
$1,360
2024-12-31
CENSUS_ACS5
zcta 40475
acs median gross
$911
2024-12-31
CENSUS_ACS5
zcta 40475
acs recent mover gross
$1,037
2024-12-31
CENSUS_ACS5
zip 40475
payment standard 110
0
$759
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 90
0
$621
2025-10-01
HUD_USER_SAFMR
zip 40475
safmr
0
$690
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 110
1
$902
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 90
1
$738
2025-10-01
HUD_USER_SAFMR
zip 40475
safmr
1
$820
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 110
2
$1,045
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 90
2
$855
2025-10-01
HUD_USER_SAFMR
zip 40475
safmr
2
$950
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 110
3
$1,452
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 90
3
$1,188
2025-10-01
HUD_USER_SAFMR
zip 40475
safmr
3
$1,320
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 110
4
$1,639
2025-10-01
HUD_USER_SAFMR
zip 40475
payment standard 90
4
$1,341
2025-10-01
HUD_USER_SAFMR
zip 40475
safmr
4
$1,490
2025-10-01
HUD_USER_SAFMR
ACS median gross rents and HUD FMR/SAFMR for the facility's county and ZIP. Context for underwriting, not facility pricing.