Solutions · By practice

Predict for MVA attorneys.

A jurisdiction-tuned gross case value for motor vehicle accident cases — rear-end, soft-tissue, intersection, commercial vehicle, wrongful death. Calibrated specifically to a held-out MVA fold at 88–92% median accuracy (MdAPE) on higher-value cases.

Predict your case Enter one MVA case, get a confidence-banded case value in about a minute. No signup to start. The figure is gross — before attorney fees, case costs, and medical liens.

Prefer to explore first? Try the free MVA valuation →

Inside the workspace · an MVA case
Illustrative example. A Texas rear-end case in the Predict workspace — a gross case value, a confidence band, and the comparable cohort behind it. The demand letter Predict drafts in your firm's own style starts here.

The MVA case is where the carrier playbook is sharpest.

Soft-tissue rear-end with mid-five-figure med-specials is the case carriers value against an internal model every day. The plaintiff attorney working from gut + PD photos is bringing instinct to a fight that's been quantified for a decade.

Today

Anchored to property damage

Crumpled bumper → "soft case." Light contact → "lowball." The PD photo is a poor proxy for the soft-tissue cohort that actually drives case value in your jurisdiction.

With Predict

Anchored to comparable verdicts

Comparable MVA verdicts and settlements from the same jurisdiction and same injury severity tier — cohorts that run into the hundreds. The band is wide when the cohort is thin and tight when it's deep — the methodology is the answer to "how do you know?"

Today

One number, no range

"Probably worth around $80K." The carrier hears a single number with no methodology; the demand letter reads as a guess. The first offer comes in at $32K and the negotiation starts in the wrong half of the distribution.

With Predict

A defensible band

A gross case value with a 90% confidence band, cited to same-jurisdiction rear-end comparables at the matched injury severity. The demand letter Predict drafts ships with the band and the cohort, not the gut.

The MVA dataset

Trained on motor vehicle accidents specifically.

20K+
Precedent cases & 200,000 data points
The corpus is filtered for MVA before the model is calibrated — the MVA fold is the larger, denser of the two. No premises, no products, no malpractice noise.
88–92%
Held-out MVA accuracy (MdAPE)
On the held-out MVA fold, predictions land within 88–92% median accuracy on higher-value cases (median absolute percentage error). Measured on a held-out MVA test set the model never trained on, from the 2018–2025 verdict window. See the accuracy results →
Hundreds
Comparable cohort, typical case
A typical MVA prediction is grounded in hundreds of same-jurisdiction, same-severity comparables — per-state MVA cohorts run from the high hundreds into the thousands. The band widens when fewer are available — never silently.
How we know

Where the numbers come from, and how you can check them.

The settlement and verdict data is plaintiff-side only. Every record is drawn from publicly available verdict and settlement filings, plaintiff-side reported settlements, and PACER docket extracts, then filtered to MVA before the model is calibrated. No claims-side or carrier data is used in training, and none ever will be.

The held-out results are published, not asserted. We show the training data, the model architecture, the train/test split, and the held-out accuracy on the MVA fold, including how the band behaves when the comparable cohort is thin. See the accuracy results →

A defensible value at every stage of the case.

The case-selection decision on an MVA case happens at minute four of the intake call, and Predict produces a confidence-banded case value in 60 seconds. But the same valuation follows the case forward — sharpening as the police report and medical records arrive, anchoring the demand letter, and pricing the first-offer counter through settlement. Intake is one moment, not the only one. The same number carries the whole way.

The output is a number, a band, a jurisdiction tag, and the comparable cohort — a gross case value before attorney fees, case costs, and medical liens. It is the same valuation that survives a partner second-opinion or a paralegal handoff: same number, same methodology, every time.

See how it works →
Illustrative example
$148,000
± $22,000 · 90% CI
TX · MVA
Illustrative worked example — soft-tissue rear-end, low-speed impact, mid-five-figure med-specials, six months of treatment. The case carriers routinely value well below the cohort.

Where Predict fits in an MVA workflow.

With Predict
Without
Intake call
60-second predicted band, before you take the case
"Sounds like a good one" — anchored to PD photo + caller affect
Case-acceptance decision
Band ≥ firm's case-value threshold → sign the client
Sign first, value at the demand-letter draft 60 days later
Demand letter
Full demand letter drafted in your firm's style — number, band, and cohort built in
One number with no methodology — easy for the adjuster to ignore
First offer counter
Counter to the lower bound of the 90% CI, defensible on the record
Counter to a round number 20% above the offer — anchored to nothing
Second-opinion
Same model, same band, same cohort across the firm
Senior partner re-runs the gut analysis from scratch

If you already license a verdict-search database, the difference is what happens after retrieval. A verdict database gives you the comparable cases. Predict scores their similarity, weights them to your jurisdiction and injury severity, and returns a calibrated value with a confidence band, so you cite a defensible number instead of a stack of comps you still have to value by hand. Predict vs. a verdict-search database →