NERVE — Network Earnings & Risk Visibility Engine

Project NERVE v14-AI | Model v13 + AI Analytics | n=26,167 | CRITICAL 95.6% precision | HIGH 93.8% | Combined 92.8% (3mo grace) | June 2026
95.6%
CRITICAL Precision
Extended (3mo grace)
93.8%
HIGH Precision
Extended (3mo grace)
92.8%
Combined Precision
All tiers, extended
70.9%
Persistent Precision
Negative every month
75.2%
Transition Recall
Caught deteriorating
ℹ Definitions

Precision: Of lockers flagged by the model, what % actually turned/stayed negative? Higher = fewer false positives.
Extended (3mo grace): A prediction counts as correct if the locker is negative at exit month OR any of the next 3 months.
Persistent Precision: Flagged AND negative every single month from the exit onward. Strictest measure.
Transition Recall: Of lockers that genuinely went from positive to persistently negative, what % did the model catch?
Walk-forward: Train on 6 months of history, predict at exit month, validate against outcome. No future data leakage.
R²: Coefficient of determination of the OLS slope fit. Higher = more confident the trend is real, not noise.
Dual-path: Model classifies via EITHER slope deterioration OR maintenance cost spikes. Covers both failure modes.

Validation Methodology

Quarterly walk-forward (5 windows): Train on 6-month history, validate against exit month + 3-month grace period. The model never sees future data during training. Each window is independent.

Precision Definitions

Strict: Flagged AND negative at exit month only
Extended (3mo grace): Flagged AND negative at exit OR any of next 3 months
Persistent: Flagged AND negative EVERY month from exit onward

Recall Definitions

Transition recall: Of lockers that went from positive → negative (persistent), what % did we flag?
Retention recall: Of already-negative lockers that stayed negative, what % did we flag?
Overall recall: All negatives at exit / flagged (~37% — model targets deterioration, not cataloging)

Quarterly Backtest Results

WindowCRITICAL (ext)HIGH (ext)ALL (ext)Persist PrecTrans Recall
Jan-Jun2591.1%91.4%89.9%63.6%80.2%
Apr-Sep2598.1%96.2%95.6%64.9%82.2%
Jul-Dec2597.9%97.2%96.6%62.5%75.0%
Oct25-Mar2695.9%93.9%92.5%74.2%83.3%
Jan-May2694.9%90.5%89.4%89.4%55.5%

Average: CRITICAL 95.6% | HIGH 93.8% | ALL 92.8%

Miss Analysis

Understanding why the model misses helps calibrate expectations and identify improvement vectors.

Primary Miss Causes

46% — Maintenance spikes: One-off high-cost repairs that don't show as slope changes. Now partially captured via maintenance path.
23% — Seasonal rescues: Holiday volume temporarily pushes declining lockers positive. Structural limitation of any trend-based predictor.
18% — New lockers: Insufficient history for slope estimation (<4 months). Model requires 6 data points.
13% — Abrupt external events: Store closure, construction, partner dispute. No leading indicator available.