Cleaning Intensity Calibration Score (CICS)

GMI-FAC-018Facilities ManagementIntegration-Required

Definition

Correlation between AI-assigned cleaning intensity level and actual contamination load (occupant-count × duration).

The Measurement Gap

Measurement Gap and Decision

The Measurement Gap

Traditional cleaning metrics track completion (was the room cleaned?) and schedule adherence (was it cleaned on time?). Neither addresses whether the intensity matched the actual contamination. A lightly used room receiving deep-clean intensity wastes labor and chemicals. A heavily used room receiving light-touch intensity creates hygiene risk and occupant complaints.

AI cleaning systems promise to solve this by assigning intensity based on sensor data: occupancy counts, duration, event type. But without CICS, there is no way to verify that the algorithm's intensity assignments actually correlate with contamination load. The system could be defaulting to medium intensity for everything while reporting "optimized" cleaning.

The Decision It Supports

CICS tells facility managers whether the AI cleaning optimizer is actually optimizing. A high correlation means intensity tracks contamination: the system is doing what it claims. A low correlation means the algorithm needs retraining, the sensor data feeding it is unreliable, or the intensity tiers are too coarse to capture meaningful variation. This directly affects labor allocation, chemical consumption, and occupant satisfaction.

Formula

Plain Language

For each cleaning event, record the AI-assigned intensity level and the contamination proxy (occupant count multiplied by duration in hours). Compute the rank correlation between assigned intensity and contamination proxy across all events in the measurement period.

Formal Notation

$$CICS = \rho(Intensity_{assigned}, Contamination_{proxy})$$

Variable Definitions

Variable Definition Unit
Intensity_assigned AI-assigned cleaning intensity level for the space Ordinal (Light / Standard / Deep)
Contamination_proxy Occupant count × occupancy duration for the space since last cleaning Person-hours
ρ Spearman rank correlation coefficient -1 to +1

Units: -1 to +1. Values near +1 indicate intensity tracks contamination load. Values near 0 indicate no relationship. Negative values indicate the system assigns higher intensity to lower-contamination spaces.

Proposed formula, pending validation pilots.

At a Glance

Category
Service Delivery Coverage & Calibration

Decision Supported

Is the AI cleaning too lightly in high-density short-duration spaces (all-hands meetings) and too heavily in low-density long-duration spaces (executive offices)?

← Cleaning Coverage Accuracy Rate (CCAR)Consumable Forecast Accuracy (CFA) →

Assess Your Organization

The AI-GPS Assessment evaluates your AI governance maturity and recommends KPIs like this one for your implementation roadmap.

Take the Free AI-GPS Assessment