Solutions · By practice

Predict for premises liability practices.

The harder PI case. More variability by case category (slip/trip and fall, inadequate security, animal attack, and more) and a wide range of injury severities. Predict tunes the model on every one of those dimensions.

Predict your case Free PL valuation Free · 60 seconds · no signup to start. The output is a gross case value — before attorney fees, case costs, and medical liens.
Inside the workspace · a premises case
Illustrative example. A sample Miami-Dade slip/trip-and-fall in the Predict workspace. $72K predicted, ± $34K (90% band). The band is wide because the model is narrowing to the closest comparable matches and the documented damages are still moderate. Sample data, shown to illustrate the view. Run your own case to see your numbers.

PL is where the gut is least reliable.

An MVA practice sees enough rear-end soft-tissue cases to develop a defensible instinct. A PL practice sees a slip in a grocery aisle, then an inadequate-security assault, then a pool drowning — three case categories that share almost nothing. The default instinct is rarely calibrated to the case in front of you.

Today

One cohort for every PL case

"Slip-and-falls go for $40–80K." That cohort exists, but the case in front of you — inadequate-security claim, severe injury, lost-wages claim — sits inside a sub-distribution the gut average flattens away.

With Predict

Sub-categorized comparables

Cohorts split by case category (slip/trip and fall, inadequate security, animal attack, and more), injury severity, direct damages, and jurisdiction. The number is built on the slice that actually matches the case.

Today

Severity hidden in the number

A PL case with a severe, well-documented injury is a different distribution from a minor one — sometimes 2–3x. The single-number gut estimate flattens which end of that range the case sits on.

With Predict

Severity weighted in the band

Injury severity and direct damages are the top drivers in the PL model, alongside case category and jurisdiction. The band reflects how well-documented the case is — and tells you when the answer depends on discovery you haven't done yet.

The PL dataset

Trained on premises liability specifically — and honest about the harder cases.

20K+
Precedent cases & 200,000 data points
Premises cases from the 2018–2025 verdict-and-settlement corpus, after deduplication and the 4-year rolling cut-off. The PL fold is the thinner of the two, in line with the underlying market.
87–93%
Held-out PL accuracy (MdAPE)
Median accuracy on cases the model never saw during training (held-out test set, 2018–2025 verdict window), on higher-value cases. See the accuracy results →
7
Case categories
Slip/Trip and Fall, Animal Attack, Inadequate Security, Building Maintenance, Drowning Risk, Fire & Chemical, and Other. Each modeled separately before the cross-jurisdiction tune.

PL is where the confidence band earns its keep. When the matching cohort is thin or the documented damages are still soft, the band widens, and that's the signal to slow down on case selection, not to ignore the model. See how it works →

A wider band is still better than a wrong gut.

A PL case whose closest comparables are sparse gets a wider 90% confidence interval — the methodology forces honesty about uncertainty. That is the input to the case-selection decision, and the same band carries forward through demand-letter prep and negotiation as discovery fills in. A $40K–$110K band tells you the case can pay if worked, and it tells you the upside isn't a guarantee. Every figure is a gross case value — before attorney fees, case costs, and medical liens.

The default tool — gut + a senior partner's recall — produces a single number with no uncertainty surface. The number feels more confident; it isn't.

See how the confidence band works →
$72,000
± $34,000 · 90% CI
FL · MIAMI-DADE · PL
Wider band than a typical MVA case — sparser close matches, damages still moderate. The band is the answer.

Where Predict fits in a PL workflow.

With Predict
Without
Versus a verdict database
One jurisdiction-tuned number with a 90% band, built only on the sub-cohort that matches case category and injury severity
A list of past verdicts you weight and average by hand. No uncertainty surface, no severity-weighted filter
Case categorization
Case category, injury severity, direct damages, jurisdiction
"It's a slip-and-fall" — one category, broad cohort
Intake decision
You set a value your firm needs a case to clear before you take it. Predict shows whether the case clears it, and flags a wide band as "run discovery before you take the case" — then the same number carries through demand-letter prep and settlement
Take it if the senior partner has time to look at it
Injury severity & damages
Top drivers in the model; band widens when the damages are still soft
Carried in the attorney's head; rarely changes the number
Demand letter
A full demand letter drafted in your firm's own style and formatting — number, band, and sub-cohort built in, exportable to PDF/Word
One number with no methodology — defense counsel pushes the carrier to ignore it
Wide-band cases
Flagged for senior review before you take the case
Discovered at depositions, 6 months and $40K of paralegal hours later