We developed a platform that used data analytics to identify suspicious claims and reduce wrong claims.
With over 50 years of experience providing health insurance options to commercial businesses, individuals, and Medicare/Medicaid patients, our client was looking to update their platform and digitize their processes in order to increase efficiency, reduce computational errors, and identify fraud.
Problems That Needed To Be Addressed
As a major player in the health insurance industry, our client was following business processes, practices and government regulations that had been in place for decades, thus resulting in more operational and resource costs. Additionally, their processes failed to capture misinformation or fraud thus resulting in losses through wrong insurance claims.
The Solutions We Provided
The Expeed team analyzed the problem areas and came up with multiple analytical solutions using Data Science, Machine Learning. We also developed a Web and Mobile application that allowed the new features to capture data and present them for evaluation in a much easier way.
The Impact and Long-term Results
The client started saving thousands of dollars every month which was otherwise lost on payments to wrong claims. The process also helped in better resource utilization resulting in long term patients getting better service. Improved customer satisfaction helped boost the brand value of the company.
We developed a solution using multiple Machine Learning techniques to identify all the suspicious claims. This prevented wrong claims from happening in the first place and also reduced the cost and effort spent on recovering wrong claims each year.
So, Here’s How We Did It
Financial Recovery Analytics: The insurance industry in general, and our client in particular, receives a number of claims from healthcare providers with wrong amounts and wrong procedure codes.
Our client’s claims processing system failed to catch these invalid claims, resulting in hundreds of millions of dollars of payments towards these invalid claims. This had been a known problem and our client spent close to 200 million dollars in efforts towards recovering only a portion of these wrong payments.
We developed a solution using multiple Machine Learning techniques to identify all the suspicious claims based on the recent amendments to the underlying contracts, comparison of the distribution of claims across procedure codes between different pay periods, and comparison of price distribution for procedure codes between different pay periods. This gave a much smaller set of all claims with potential issues and the recovery team was able to act on all of them instead of randomly picking a few of the claims from the whole set. This reduced the cost of the effort to recover and prevented wrong claims from happening after a month. It resulted in significant financial savings to our client.
Complaint Response SLAs: Our client’s existing system was unable to meet the SLAs that were required in order to respond to customer complaints, resulting in penalties. To overcome this problem, our client outsourced the activity of manually reviewing each of the complaints and assigning them to the appropriate department. This manual process was costing a significant amount of money and was sometimes error-prone resulting in further penalties.
Our team stepped in to resolve this problem through process automation where we used the techniques of text mining, sentiment analysis and machine learning algorithms. With this new automated system, our client was able to eliminate the cost of a 40-member outsourced team and significantly improve the chances of meeting SLAs through more accurate prediction of the department that can address the issue based on the text of the complaint.
Long Term Medicaid Services Process Optimization: As part of Medicaid program, our client provides long term care services to Medicaid patients. As part of the program our client employs a number of care coaches and third-party service providers to attend to the needs of Medicaid patients. But there were inefficiencies in the system of care coach assignment and need-evaluation of the patients, which was resulting in revenue loss and fraud.
Our team developed an application to recommend the assignment of care coaches to patients with the goal of minimizing the distance they travel and maximizing the time they spent with the patients, with a near-uniform distribution of workload among care coaches. This resulted in multi-million-dollar travel-related savings, better results for patients, and work-life balance to care coaches.
We also used Machine Learning techniques to better evaluate the individual needs of every patient. We took the patient’s medication history and predicted services they would benefit from. Care coaches started using those recommendations while offering services to the patients. This resulted in cost savings, happy patients, and reduced the scope for fraud that could be involved in offering services.