Predictive modeling
See the whole curb, not just the part that paid.
Occupancy, duration, and noncompliance on every Curb Zone, every hour. No new hardware required.
Every data source has blind spots.
Payments miss who didn’t pay. Studies and sensors miss what they can’t reach. Predictive modeling fills the gaps.
Sullivan Street
Paid
62%
Modeled
87%
Lincoln Avenue
Paid
58%
Modeled
79%
Knope Way
Paid
67%
Modeled
93%
Sussex Lane
Paid
46%
Modeled
64%
Ludgate Street
Paid
49%
Modeled
68%
Sullivan Street
Paid
62%
Modeled
87%
Lincoln Avenue
Paid
58%
Modeled
79%
Knope Way
Paid
67%
Modeled
93%
Sussex Lane
Paid
46%
Modeled
64%
Eagleton Place
Paid
54%
Modeled
72%
The full picture, from data you already have.
Turnstone estimates what happens on every Curb Zone, including parking that never shows up in a transaction.
Payment
Permit
Citation
Inventory
LPROptional
Parking studiesOptional
Occupancy
74%
Duration
1.88 hrs
Noncompliance
4.1%
Three answers for every Curb Zone.
One set of numbers for your parking, planning, and enforcement teams.
Occupancy
74%
↑ 4% YoY
Jun · 79%
Highest Occupancy
86% / 81%
83% / 79%
77% / 74%
71% / 68%
Duration
1.88 hrs
↑ 0.12 hrs YoY
Apr · 1.95 hrs
Longest Avg Duration
2.15h / 2.05h
2.08h / 1.99h
1.98h / 1.90h
1.92h / 1.85h
Noncompliance
4.1%
↓ 0.8% YoY
Mar · 5.5%
Highest Noncompliance
41% / 37%
39% / 36%
34% / 35%
29% / 28%
Know where to check. Turnstone handles the rest.
Turnstone flags the Curb Areas that need a closer look. Once a sample comes in, Turnstone handles the rest.
Parking Behavior Change Analysis
Curb Area: AllOct 2025 to Sep 2026
OctNovDecJanFebMarAprMayJunJulAugSepDowntown Core2.3%3.1%1.8%2.7%3.6%2.2%4.4%3.9%7.4%5.2%4.7%3.3%Pawnee Commons1.2%0.9%1.6%2.4%1.9%1.3%2.8%3.2%2.1%1.7%2.6%1.4%Ramsett Park3.8%4.6%5.1%4.2%3.5%4.9%7.9%6.1%5.4%4.8%5.7%6.2%City Hall2.9%2.5%3.4%9.1%4.3%3.7%2.6%3.2%3.6%2.8%3.1%2.4%Lot 484.8%5.3%6.4%5.9%4.5%5.6%12.6%6.7%5.1%4.3%5.8%4.9%Eagleton1.5%2.1%8.3%3.4%2.7%1.9%2.2%1.6%2.5%2.9%2.3%1.8%Lower Pawnee3.2%2.8%3.7%3.9%3.3%4.6%5.2%5.9%6.3%9.6%13.2%17.9%Riverside0.7%1.8%1.4%0.6%1.3%8.6%1.3%1.7%1.2%0.9%1.5%1.6%
StableWatchValidate
Validation source
Manual counts
Vehicle-mounted LPR
Drone
Cameras and sensors
Other
FlaggedLower Pawnee
Collection requestedOct 14, 2026
ValidationAutomatic once data arrives
- Flagged
Shifts in parking behavior show where to look.
- Collected
Gathered however works best for your program.
- Automated
Turnstone validates the model and folds the results back in.
Guided enforcementRead the case study
Using Predictive Modeling to Guide Enforcement in Berkeley, CA
53%of noncompliance concentrated in the top 20% of Curb Zones
+13.6%short-stay parking sessions
-26.1%long-stay parking sessions
“Turnstone gives us one place to see how the curb is actually behaving, so we can put enforcement and pricing where it will do the most good.”
Elliott SchwimmerSenior Transportation Planner, City of Berkeley
