Scored the moment it lands.
A traceable score you define, updated instantly on any change.
A score you can take apart. Combine deterministic appetite with ML or AI decisioning with full understanding of how each factor contributed.
Build a unified score.
Structurally break down appetite to targeted rules while maintaining a holistic comparison cross policy.
Weight and mod attributes.
Group appetite into categories, weight them against each other, and modify how hard a single weak input is allowed to drag or promote.
Use our ML or bring your own.
Deploy riska's out of the box ML attributes or connect your own all within the same framework.
Best in class traceability.
Data changes, policies evolve with new information and appetite shouldn't lag. Understand the appetite progression and what's live now.
“The first week we ran it we found we were declining more habitational than anyone in the room believed.”
Four ways to turn a value into a score. Pick one per dimension. A construction class is not a loss ratio, and neither belongs on the same curve.
Tiers.
Bands, each with a score. A five year loss ratio under 40 percent scores 100, over 100 percent scores 0, and where the bands fall in between is your call.
Curves.
For quantities where a bucket edge would be arbitrary. Interpolate along a line, an S curve or a log curve, so total insured value moves the score smoothly instead of in steps.
Static.
Presence is the whole signal. Sprinklered scores 90, and a blank scores whatever you decided a blank is worth.
Pass-through.
The value already is a score. A wildfire rating that runs 0 to 100 goes in untouched.
Appetite as action. Appetite shouldn't just be a number to look at. Automate any result based on live appetite change.
Knockouts
Out of appetite. Recorded against the rule that fired and the score that put it in range.
Referrals
Inside appetite, but not without a person. The note you wrote on the rule travels with the result.
Custom workflows
Trigger any platform effect the instant a policy falls in or out of appetite.
Audit historical decisioning. Every change is recorded and filed. History is what makes a decision defensible and improvable six months later.
Point in time decisioning.
Open any scored version and see the final score with its breakdown. Have confidence the decisions of today are explainable in the future.
Appetite as a feedback loop.
Turn appetite in a living model that improves over time. Compare reports of good and bad business against appetite so you improve your pipeline today from lessons learned yesterday.
Book wide.
Unified scoring powers cross book understanding. Evaluate from the book level how each product line, workspace, team and org is performing in the same view.
Underwriting, end to end.
Appetite is one decision in a longer path. The rest of the platform carries the same record from intake through renewal.
Universal data for any appetite
See how our proprietary query engine allows for immediate appetite definition. We will encode a few of its rules and score a live policy against them.
Usually 30 minutes, with an underwriter on the call.