Akur8 Publishes New Research Paper “Credibility and Penalized Regression”
NEW YORK, March 29, 2022–(BUSINESS WIRE)–Akur8 today released a new research paper for the actuarial community titled “Credibility and Penalized Regression”. Developed by a senior team of actuaries and data scientists at Akur8, the goal of this new article is to provide practitioners with key concepts and insights that demonstrate how penalized regression combines generalized linear models (GLMs) with assumptions credibility type.
In recent years, a number of adaptations to GLMs have been developed to address certain limitations, such as their inability to incorporate credibility-like assumptions. These adaptations are widely adopted within the machine learning community, but they have not been very popular in the actuarial world. Credibility methods and GLMs are part of the standard actuarial toolkit of predictive modeling, but the actuarial literature describing how penalized regression mixes credibility with GLMs is not equally developed.
“In exploring how penalized regression (and Lasso in particular) can be interpreted from the perspective of both credibility and GLM frameworks, the goal of this article is to familiarize practitioners with penalized regression as a extension of established actuarial techniques, instead of considering it as one of several new modeling techniques emerging from the Machine Learning and Data Science literature,” noted Guillaume Beraud-Sudreau, Co-founder & Chief Actuary at Akur8.
“Our team of actuaries and data scientists at Akur8 worked closely together to produce this comprehensive research paper on credibility and penalized regression. We are delighted to publish this information with the aim of helping to expand the literature available to the actuarial community on this important subject” said Samuel Falmagne, co-founder and CEO of Akur8.
Specifically developed for actuaries and predictive modellers, Akur8’s solution improves insurers’ pricing processes by automating technical and business premium modeling using proprietary transparent machine learning technology. Key benefits for insurers include reduced data preparation and modeling time, effectively accelerating time to market and producing more predictive models, while ensuring full transparency and control of the models created .
The document can be downloaded here: https://bit.ly/Akur8-Credibility-And-Penalized-Regression
Akur8 is revolutionizing insurance pricing with transparent machine learning, empowering insurers’ pricing capabilities with unprecedented speed and accuracy throughout the pricing process without compromising auditability or control. Our modular pricing platform automates technical and commercial premium modeling. It allows insurers to calculate adjusted and accurate rates in line with their business strategy while having a significant impact on their business and maintaining absolute control over the models created, as required by national regulators. With Akur8, the time spent modeling is divided by 10, the predictive power of models is increased by 10% and the potential for loss ratio improvement is increased by 2 to 4%. Akur8 already serves more than 40 customers in more than 20 countries, including AXA, Generali, Munich Re, Tokio Marine North America Services (TMNAS); specialty insurer Canopius and MGA Bass Underwriters; consulting partners Xceedance and Perr & Knight; and insurtechs Bought by Many and wefox. More than 600 actuaries use Akur8 daily to create their pricing models across all industries. Akur8’s strategic partnerships include Milliman, Duck Creek, Guidewire and Sapiens.
See the source version on businesswire.com: https://www.businesswire.com/news/home/20220329005006/en/