CCC Intelligent Solutions (CCC) has become the first company in the auto insurance industry to deliver an AI-powered repair estimating solution, called CCC Estimate – STP, short for straight-through processing.
The Chicago-based auto-claims technology powerhouse uses AI, insurer-driven rules and CCC’s vast ecosystem to deliver repair estimates in seconds, instead of days. It’s a technological feat considering there are thousands of vehicle makes and models on the road, and countless repair permutations.
The company’s commitment to AI spans many years, with its first AI solutions hitting the market more than five years ago. Today, it’s working to bring AI and intelligent experiences to key facets of claims and mobility for its 30,000 customers, who process more than 16 million claims annually using CCC solutions.
“Our data scientists play a crucial role in creating new solutions and the ability to build models, experiment and easily integrate the model into our AI workflows is key,” said Reza Rooholamini, chief scientific officer at CCC.
CCC has four decades of expertise in automotive claims and collects millions of unstructured and structured automotive-claim data points every year. The combination of industry experience and raw data, however, is just the starting point for CCC’s efforts. The company runs a 100% cloud production environment, providing customers with a flexible platform for continuous innovation.
As a market leader, CCC regularly reports AI adoption among its customers to track progress. According to its 2023 AI Adoption report, the company reported that more than 14 million unique claims have been processed using CCC’s computer vision AI through 2022. The company also saw a 60% year-over-year increase in the application of advanced AI for claims processing.
And AI isn’t just being used to process more claims, it’s informing more decisions across the entire claims management experience. In fact, the number of claims processed with four or more of CCC’s AI applications has more than doubled, year-over-year.
CCC has built an end-to-end hybrid-cloud AI development and training pipeline to support its continuous innovation. This infrastructure uses over 150 NVIDIA A100 Tensor Core GPUs, including NVIDIA DGX systems on premises and additional resources within NVIDIA DGX Cloud.
The CCC development teams are using DGX Cloud to supplement on-prem capacity, support supercomputing demand spikes and accelerate AI model development overall.
“The AI pipeline we’ve built enables us to unleash all kinds of innovations,” said Neda Hantehzadeh, director of data science at CCC.
With 25-30% of its data scientists and engineering teams’ time dedicated to experimentation, coupled with massive datasets that are growing each day, CCC needed to enable a more scalable, multi-platform, hybrid multi-cloud for its training environment.
Using its AI pipeline, CCC launched CCC Estimate – STP, which can deliver a detailed line-level estimate of the collision repair cost based on insurer rules in seconds using AI and just a few pictures of vehicle damage taken from a smartphone. Traditional methods can take several days.
This saves time for adjusters, freeing them up for more complex work. This digitalized estimation process helps elevate the customer experience as well as lower processing costs and is currently being used by leading insurance companies across the U.S.
But the results are broader. Using the NVIDIA Base Command Platform integrated with their development pipeline for training job orchestration and data management, the CCC team realizes improved productivity. Data scientists can run experiments 2x faster, which can mean more learnings for more innovation and solution development.
“We run some experiments on premises on NVIDIA DGX systems, but we may have spikes where we want to add, for example, 10 million more data points and do another run,” Hantehzadeh said. “If we need additional capacity, we can switch to DGX Cloud. Base Command Platform makes this process seamless.”
CCC plans to continue taking its investment to the leading edge of AI development, injecting AI and STP into different channels and products across the property and casualty insurance economy.