Mercer is a human resources consulting firm and the world’s largest outsourced asset manager. Headquartered in New York City, Mercer has over 25,000 employees and operates in more than 130 countries.
The processing of insurance renewals and quotations depended on the analysis of experienced staff. The entire process was time-consuming and error prone. Supervisors had to perform multiple checks to review sensitive information and ensure accuracy because of changes in business processes and to meet regulatory and compliance standards (HIPAA, PCI, tax laws, etc.). Their existing OCR platform needed constant intervention as it struggled with the variability of document formats and with data complexity. This resulted in longer renewal times which led customers to seek other insurers and hit revenue.
Cognitive Machine Reading (CMR), a combination of AI, cognitive technology, Machine Learning and pattern recognition, enabled data classification and extraction of structured and unstructured documents, including handwriting and images, from multiple document formats. Mirroring human data processing methods it extracts key data elements, automatically categorises healthcare claims, providing curated data for downstream systems. CMR automatically flags missing or unreadable information as exceptions and routes tasks to the right people. Each manual intervention improves the accuracy and confidence of CMR’s Machine Learning models.
After CMR was implemented, Mercer saw accuracy rates of at least 76% meaning fewer hours spent handling exceptions and lower costs per quote. CMR cut processing times by 70% leading to faster turn-arounds for each request, higher customer renewals/new accounts and increased revenues.