Machine Learning and Artificial Intelligence are transforming the insurance industry by pairing traditional actuarial methods with data-driven insights to disrupt the older ways of doing business. Forward-looking insurance companies are embedding analytics into every aspect of their organization, from assessing underwriting risk and optimizing claims management, to detecting fraud, waste, and abuse, and utilizing the myriad of sensor data made available by their customers.

We have experience helping large insurance companies develop AI/ML and data strategies, train practitioners across business lines in data literacy and data science, and deliver actionable insights through predictive models and data visualization tools.

Some sectors where we have worked include:

  • Life Insurance
  • Long-term Disability Insurance
  • Long-term Care Insurance
  • Property and Casualty Insurance
  • Reinsurance
  • Health Insurance (see Healthcare page)

Elder Research has decades of analytics consulting experience leveraging information about policyholders and claims to help our insurance clients. In addition to practical data science application, we have assisted many insurance organizations with training, organizational data and analytics strategy, and model risk evaluation. Other examples of our insurance analytics consulting services include:

Claims Analytics

From insurance claims prioritization and forecasting claims volume, to improving claims approval speed and accuracy, we help streamline the insurance claims process while reducing cost by:

  • Improving underwriting risk management
  • Increasing claims approval speed and accuracy
  • Improving claim management resource utilization

Insurance Fraud, Waste, and Abuse Analytics

With a long history of detecting service provider and insurance claims fraud, and aiding in the recovery of funds lost to fraud, waste, and abuse, we help insurance companies:

  • Prioritize investigative caseload
  • Increase efficiency of investigative resources
  • Increase recovery, restitution, and cost avoidance
  • Learn more about fraud analytics.

Worker’s Compensation Insurance Analytics

The complexity and volume of claims from an aging workforce, a growing dependency on and inappropriate use of prescription drugs, fraud, and increasing obesity and other comorbidities, are key factors driving skyrocketing treatment and lost work costs in worker’s compensation insurance. Predictive analytics is quickly becoming an essential capability to evaluate risk and avoid unnecessary expenses. Our worker’s compensation analytics can:

  • Decrease improper payments
  • Prioritize cases for utilization reviewers based on risk
  • Minimize total claim costs
  • Suggest early interventions to improve outcomes

Request a Consultation

Contact Us

Case Studies

There are many opportunities to apply analytics in insurance and reinsurance. We have the experience to strengthen and grow your company’s insurance analytics initiatives, whether you are new to analytics or looking to augment existing capabilities.  Examples of our insurance solutions include:

Optimizing Federal Workers Compensation Claims Approval

Elder Research developed a data-driven risk assessment framework to triage Worker’s Compensation claims, prioritizing high risk cases for review and fast-tracking other cases to avoid manual review and adjudication. Claims that are routed to the fast track are assigned risk-based maximum payment limits for intelligent ongoing claims management.

Results: Claims examiners use the risk assessment framework to triage Worker’s Compensation claims, prioritizing high-risk cases for review and fast-tracking other cases to avoid manual review and adjudication and to distribute case load more effectively. The expected performance improvement includes reducing the number of fast-tracked case decisions overturned by 39% and reducing total medical amount for missed denials by 25%.

Read the Case Study

Optimize the Management of Long-Term Care Claims

We provided analytics consulting services to improve the management of long-term care insurance claims by anticipating the implications of changes in patient conditions and expanded care.  The client wanted to be more proactive helping patients and caregivers manage these changes.

Results: The model predicted escalation in claim invoice amounts months in advance, enabling the client to accurately identify cases likely to benefit from proactive intervention. This led to greater efficiency in claims management and improved customer experience.

Read the Case Study

Improving Claims Approval Speed and Accuracy

We combined text mining with traditional statistical techniques to create an analytics solution for ranking disability claims for approval. For the Social Security Administration identifying claims for disability that met the requirements for approval was a time-consuming and error-prone process. Some claims were taking over two years to be processed, much too long for very ill or elderly claimants. The challenge was to effectively integrate the data.

Results: The solution allowed 20% of the claims to be approved immediately, allowing the organization to focus resources on the most challenging cases and ensure that all statutory requirements were met.

Read the Case Study

Detecting Health Insurance Fraud, Waste, and Abuse

We developed a predictive fraud detection model that scored and ranked Medicare and Medicaid dental insurance claims by risk. Having explainable scoring was a key component of success, since the model results would be used as evidence to warrant opening an investigation for providers identified as suspicious.

Results: The solution generated leads with the highest potential return on investment for investigators and increased the fraud detection rate from 5% to 48% for the top 50 riskiest providers identified by the model.

Read the Case Study