Skip to Content

The Causal AI conference is back in San Francisco for 2024, bigger and better than ever.

Register Interest

Leading Global Insurer sees a multi-million $ reduction in auto claim costs when using Causal AI


Top Global Insurer


Auto Insurance

Use Case

Insurance Claim Costs


Multi-million $ reduction in auto claim costs

The Challenge

The leading global insurer processes $100s of millions in motor insurance claims per year. They invested in a series of initiatives to reduce these costs, including a network of partner garages. They are interested in understanding how this network drives (if any) a reduction in auto claim costs and how they can further reduce these costs through customer incentives.
However, traditional methods were unsuitable for solving this problem:

Many potential confounders

There were many potential confounders, e.g., are claims for network garages cheaper than equal claims, or do customers leverage the partner network only for minor repairs?

Can't run 'what-if analyses'

They require the ability to run counterfactuals and interventions to develop optimal policies to reduce costs.

Not utilizing their team's domain knowledge

The customer’s team has a great deal of domain knowledge and requires an efficient way to integrate this into the modeling process.


The problem required a causal understanding, and the customer team turned to decisionOS for a solution. Using decisionOS, our Causal AI platform, they were able to:

    1. Understand and quantify the causal drivers of claim costs, accounting for potential confounders.
    2. Run “what-if” analyses to develop new optimal policies to reduce costs.
    3. Integrate their domain knowledge into the modeling process, combining the best of domain experts and data-driven approaches.

Results and Benefits

Leveraging decisionOS, this leading Global Insurer was:

    1. Able to quantify the causal impact of repairs taking place in-network, uncovering a multi-million dollar cost reduction opportunity.
    2. Able to identify how costs were impacted across different incident types and which incidents they should create incentives for in-network.
    3. Able to determine new enticements to drive down costs, identify which garages to keep or remove from their network, and create optimal pricing for policies.
    4. Able to identify, in the long-term, how inflation impacts different types of claims and how to adjust their policy pricing moving forward.

As a global insurer that processes $100mns in motor insurance claims annually, they must invest in technology to reduce these costs. By identifying, understanding, and quantifying the causal drivers of claim costs, running a “what-if” analysis to decide on optimal policies for price reduction, and maximizing the use of their team’s domain knowledge, this customer was able to identify multi-million $ cost savings.

By merging industry-leading technology and the customer’s domain expertise, this example highlights a clear path for Causal AI to be the technology that Global Leaders in the insurance sector invest in across multiple use cases.

Start your Causal AI Journey

Request a Demo