Call us at 650-400-3029 (PST)

Reducing the cost of Manual Claims Handling

Our CTO, Ryan Trollip, recently gave a webinar on claims automation with our partner Red Hat. Many companies spend heavily automating their claims process, but this spend is largely on handling a claim efficiently not on claims handling effectiveness. Digitizing claims documentation and the claims workflow might help pay a claim more cheaply, but it does little to ensure that the right claims are paid or that the right approach is taken. Our customers invest in digital decisioning to make sure that their claims handling decisions – which claims to pay, when to investigate, when to fastrack – are also digitized. This focus reduces fraud and waste, assigns the right people at the right time and has a bottom-line impact on loss ratios.

In this series of blog posts – there are two more to come – I’m going to use three specific claims business problems to illustrate how this focus on digital decisioning adds business value.

Business problem – manual claims decisions

Some years ago, we worked with a health insurer with a typical manual claims process. Claims were completely digitized, but every claim was manually reviewed. This kept costs high and damaged customer satisfaction – customers REALLY want their claims paid fast. The insurer had made lots of technology investments in new channels like chatbots, mobile applications, online claims submission and even API-based submission direct from hospitals. None of this improved customer service or satisfaction though – because it still took too long to decide if a claim should be paid.

Solution – business-led continuous improvement

To fix this problem, we delivered a digital decisioning solution. We developed a visual blueprint of their manual decision-making – a decision model – to capture their best practices and business know-how. This was quickly implemented as a set of business rules in a decisioning platform. We set up a simulation environment and a decision outcomes dashboard so the claims team could see how decisions were being made and how a change to their rules would impact results. Machine learning models were developed to make critical predictions about claims, and these were integrated with the business know how of the claims team. Finally, business owners were empowered to make changes that would improve results. Every week they would review results, identify improvements, simulate the impact of those changes, and deploy the ones that were worthwhile.

Results – straight through processing and customer satisfaction

The team’s analysis was that improving customer satisfaction would need 1 in 5 claims to be approved or rejected without manual review. This 20% straight through processing target had to be met without increasing fraud risk or overall claims cost.

When the digital decisioning solution was first integrated with the claims process, just 8% of the claims were auto adjudicated. These were the ones everyone was confident in, where there was no ambiguity. This ruthless focus meant the claims team could be confident that there would be no negative consequences of the automation.

And then the weekly update cycle kicked in. Every week the rate of auto adjudication and straight through processing rose. By day 100 they had passed their target and had hit 28%. By day 250 they had hit their stretch goal of 50% – there were data issues that made much more than 50% unrealistic.
This business-led decision automation had vastly exceeded their targets in just a few months of operations. Fraud and waste were being managed correctly, customer satisfaction was up and costs were down.

Learn more about how digital decisioning can improve your claims handling by watching our webinar or contact us with questions about how we could help you with your process.

Amit Rawool

Amit Rawool

AI/ML developer

Amit Rawool

Amit Rawool is a seasoned Python Developer, with nearly a decade of experience in the field of machine learning, computer vision, natural language processing (NLP), reinforcement learning, and large language models (LLMs). His technical prowess is complemented by his ability to develop scalable applications using modern technologies like FastAPI, React, and Next.js.

Amit’s academic journey includes a Master of Technology from the Indian Institute of Technology Bombay and a Machine Learning Certification from Stanford University. Throughout his career, Amit has held various impactful roles, including Consultant Machine Learning Engineer, Research Engineer, and Lead Engineer, across prestigious organizations such as General Electric, General Motors and Sandvik Asia. He has led and contributed to several high-profile projects, including a real-time data processing system, and an AI-based product recommendation system.

Amit’s work is characterized by his innovative approach to solving complex problems and his commitment to integrating cutting-edge technology solutions. His expertise extends across a broad spectrum of software skills, including Python, JavaScript, PyTorch, TensorFlow, and OpenAI GPT models.