Enhanced quality assurance at a leading health benefits administrator

Enhanced quality assurance at a leading health benefits administrator


A large health benefits administrator wanted to enhance the quality and efficiency of their existing claims auditing processes. These processes were mostly done manually and they were often reliant upon a claim auditor’s subjective judgment. Errors or oversights in the auditing process resulted in medical inefficiency, unnecessary overspending, and poor performance on the organization’s external audit. They needed to enhance existing processes by incorporating automated processes to help identify and correct errors.  


Neal Analytics developed a machine learning model to identify and target the root causes of the most common errors in current auditing procedures. We designed a model to learn and optimize rules on top of existing processes to proactively flag and hold potential erroneous claims before being paid out. Neal Analytics also implemented a feedback loop for machine learning algorithms to receive and process follow-up information for continuous automated improvement and adaptability to new challenges and circumstances.  


The solution resulted in significantly reduced error rates in processed and audited claims. There was an overall improvement in results from external audits as well as client feedback. With this solution, the administration enabled the auditing team to effectively incorporate advanced analytics to widen its coverage scope without significantly increasing resource expenditure.