Tech chat: Scaling our systems to supercharge AI performance

Performance blog - why we thought we were cool

In our last blog, we shared the results of recent performance testing which revealed our AI can process 1,000,000 quotes a week. Now, Nuon Founding Partner Richard Anderson takes you on a deep dive into the tech behind those numbers, giving you a glimpse into the day in the life of our Engineering team.

How we use visual tools to build Nuon AI

Nuon AI dashboard icon

To help us – and our customers- understand the workings of Nuon’s AI algorithms we use visual tools. These help us track how the AI is hanging together, as well as provide our customers with real-time insights into how their products are performing.

How Nuon AI works…

Nuon - How to?

This real-world simulation shows how the Nuon algorithm identifies and responds to a competitor who makes a factor change. This particular scenario sees a price reduction on a motor product for legal cover.

Within two hours, the insurer using Nuon has learned, adapted and recovered its conversion rate.

Why reinforcement learning for insurance pricing?

Reinforcement learning / Nuon AI

The heart of Nuon’s Artificial Intelligence software is a set of proprietary algorithms based on Reinforcement Learning (RL) So why do we use RL? In simple terms, RL allows us to run experiments on live quotation and sales data – and learn from them.