Akur8 RISK

Create a vendor selection project
Click to express your interest in this report
Indication of coverage against your requirements
A subscription is required to activate this feature. Contact us for more info.
Celent have reviewed this profile and believe it to be accurate.
We are waiting for the vendor to publish their solution profile. Contact us or request the RFX.
Projects allow you to export Registered Vendor details and survey responses for analysis outside of Marsh CND. Please refer to the Marsh CND User Guide for detailed instructions.
Download Registered Vendor Survey responses as PDF
Contact vendor directly with specific questions (ie. pricing, capacity, etc)


Akur8 automates the rate modeling process while preserving absolute control and transparency thanks to Akur8’s unique proprietary algorithms powered by Transparent AI.

Akur8 allows for dramatic gains in modeling time (10x faster) and a strong increase in predictive power (+10% Gini) for a much higher speed-to-accuracy. This leads to both quicker time-to-market and greater accuracy in decisions made.

Akur8 RISK module allows actuaries and pricing teams to model rosk and compute full technical premiums, in a much faster, more performant and safer way. By automating the data-driven part of the process, Akur8 enables actuaries and pricing teams to leverage their business expertise and focus on the most value added part of the process.

Generate, select, adjust, enrich and aggregate your risk models to build pure premiums faster, leveraging machine learning to focus on tasks where your business expertise can add even more value.

Key Features

Akur8 brings speed, performance and transparency to rate modeling, thanks to proprietary algorithms powered by Transparent AI. Specifically designed for insurers, it offers a unique combination of actuarial modeling and data science, generating models that are production-ready, based on models actuaries know and use: Generalized Additive Models (GAMs) and Generalized Linear Models (GLMs).

Akur8 goes beyond classic black-box Machine Learning (ML) like Gradient Boosting Machines (GBMs), to deliver a fully transparent output, removing traditional risks associated with blackbox AI. Akur8 leverages machine learning to automate the rate making process, allowing clients to build models that are on par with GBMs or Random Forest in terms of performance, eventually offering the best trade-off possible between high performance and control & interpretability.

Akur8’s performance is reinforced by strongly-differentiating native features that are traditionally not integrated in legacy solutions, such as automatic geographical zoning, automatic suggestion of the most relevant interactions or automated vehicles classification. The solution also allows insurers to seamlessly incorporate external data to improve the predictive power of the models.

Key Benefits

With Akur8, insurers can automate their pricing process while keeping complete control of it, with concrete benefits enticing substantial economic gains :

Speed: with Akur8, modeling time is dramatically decreased, generally by 10x

Performance: with Akur8, the predictive power of models is increased by 10% on average

Transparency: outputs generated with Akur8 are fully transparent, with a robust process allowing for smooth communication and improved governance

The pricing models generated by Akur8 are ready to go in production: they are fully transparent, auditable and editable, which strongly differentiates Akur8 from generic blackbox AI platforms.

Akur8’s platform is fully collaborative. Multiple users can use it at once, while ensuring that all changes are visible and well traced.

Akur8’s Transparency goes beyond AI: for each project, key assumptions of the rate making methodology can be automatically exported and shared within the organization. This allows solid governance, smooth communication, great visibility and transparency for insurers.


Case Studies

Product/Service details