Underwriting
Underwriting has always priced the answers. ForMotiv adds how they were given: what changed as they went, and what came back different on a later visit. You see misrepresentation, premium leakage and nondisclosure in session, in real time, and after the quote.
Applicant begins an auto quote online.
Fourteen minutes of answers and edits, then a return visit two days later. Only the final values reach your systems.
$1,042 for six months.
Applicant comes back and buys online.
Drivers
1
Vehicle use
Commute
Prior carrier
3 years
Garaging ZIP
19103
OutcomeBinds as submitted at $1,042
Session established; device and network recorded.
Paused 11 seconds on “Any other drivers?” and answered No.
Undisclosed driverPicked Business, then switched to Commute before moving on.
Misrepresentation$1,388 for six months.
Tenure changed from 8 months to 3 years.
Rate evasionSame device. Moved the garaging ZIP, then bound.
Location gamingHigh-risk signals fired during the session and on the return visit.
One illustrative application of many. Some changes happen before a price is ever shown, and some days later. ForMotiv captures both.
What underwriting teams use ForMotiv for
Three of many. Each leaves a different behavioral trail, and ForMotiv captures it in session, in real time, and after the quote, including return visits. Version history can tell you what changed between saves. ForMotiv shows the behavior behind it, as it happens.
Drivers left off, mileage trimmed, garaging moved and tickets deleted, whether that happens while the form is being filled in, after a price appears or on a later visit.
A few examplesUndisclosed drivers
Mileage
Garaging
Violations
Discounts
and more
Answers rewritten to get past an eligibility rule, in the same session or in a fresh one after a kickout: commercial use hidden as personal, prior carrier swapped.
A few examplesKickout & rewalk
Vehicle use
Prior carrier
Prefill overrides
and more
Tobacco, alcohol, weight and medical history answers that the applicant's own behavior contradicts, captured on the question as it's answered.
A few examplesTobacco & nicotine
Alcohol
Weight / BMI
Medical history
and more
Outcome predictions
Beyond flagging bad answers, ForMotiv predicts how an application is likely to turn out, so you can act before the policy is in force. A few of the underwriting risk models carriers use:
Likely to file a claim in the first weeks after bind.
What you can doRoute for review or verify before the policy goes in force.
Likely to miss the first payment, or stop paying soon after.
What you can doRequire a down payment or change the payment plan offered.
Likely to cancel inside the first 30 days, often after a claim or a coverage check.
What you can doHold the bind until payment or documents are confirmed.
Likely to leave before you earn back what it cost to acquire them.
What you can doTrigger onboarding or retention outreach early, or adjust acquisition spend.
Likely to be re-rated upward once the real drivers, vehicles or garaging come out.
What you can doVerify the rating answers that moved before you issue, not after.
Predict the coverage a customer is most likely to end up choosing.
What you can doQuote the right coverage up front, so you price the real risk and more shoppers convert.
Models are built around the outcomes your team cares about, and refined with your own outcome data.
The data behind the models →Agent-written business
Nobody knows your application, your rules and your rating engine better than the agents who use them every day. Most use that knowledge to write good business. A few use it to write business your guidelines were built to stop, and they're far better at it than any applicant.
ForMotiv reads every agent session, and benchmarks each agent and agency against their peers and against their own history.
An experienced agent knowsWhat ForMotiv sees
Benchmarked, not guessed. This agency removes young drivers at 3.4× the peer rate, and twice its own rate from last quarter.
ForMotiv Console
Real-time signals handle the application in front of you. The Console is where underwriting teams find where leakage concentrates and decide what to change.
Rank agents and agencies by count and severity of risk behaviors
Compare a behavior, like a young driver removed, against its baseline rate
Slice by channel, state, product and quote type
Export lists for audits, agent management and guideline reviews
Your rules and models
Use ForMotiv's signals as rules on day one, or add a DataPack to the underwriting models you already run. A DataPack is the set of behavioral features most predictive for that model.
+
→
Out-of-the-box behavioral rules built from ForMotiv's insurance expertise, configurable to your guidelines and refined with your outcome data.
Data science teams pull behavioral features by real-time API or batch to retrain pricing and early-loss models. The data stack →
Every flag arrives with the behaviors behind it, so a referral can be defended to an underwriter, an agent or a regulator.
Underwriting use cases
Premium leakage & rate evasionRating answers changed after the price.Use case → Life nondisclosureTobacco, alcohol, weight and medical answers the behavior contradicts.Use case → Quote manipulation & restartsKickout, rewalk and answer shopping across sessions.Quote & bind → Mid-term change leakageDrivers, vehicles and garaging changed right after bind.Account servicing → Agent gamingAgents and agencies who write what your rules were built to stop.ForMotiv Agent → Early-term lossesConnect how a policy was bought to the claims that follow.Claims →
FAQ
How does ForMotiv help insurance underwriting?
ForMotiv adds how application answers were given to what was answered, so underwriting teams can see misrepresentation, premium leakage and nondisclosure in session, in real time, and after the quote.
Which underwriting risk models does ForMotiv support?
Carriers use ForMotiv models for early claims, non-payers, flat cancels, early churn, uprates and coverage prediction, among others, refined with their own outcome data.
What is the difference between misrepresentation and premium leakage?
Premium leakage is underpricing caused by inaccurate rating answers. Misrepresentation is broader: answers rewritten to get past an eligibility rule, such as hiding commercial use or changing the answer that caused a decline.
Does ForMotiv replace a carrier's rating engine?
No. Carriers keep their rating engine and models and add ForMotiv signals as rules or DataPacks as model inputs.
How do underwriting teams use the ForMotiv Console?
Underwriting teams use the Console offline to find where risk behaviors concentrate, compare behaviors against baselines, rank agents and agencies, and export lists for audits and guideline reviews.
Bring one journey and one goal. We’ll show you the behavioral signals behind it, the decisions they can drive, and how ForMotiv fits into your stack.
Leakage, fraud, conversion or agent oversight, on the line and channel you care about most.
A walkthrough of the signals, features and scores for journeys like yours.
Where the tag goes, what the API returns and which systems act on it.
