By: Claim Analytics  09-12-2011
Keywords: disability, Pattern Detection

Claim Analytics, Predictive Modeling, Predictive, Model, predictive model, Insurance, Benchmarking, Scoring, Claims, Data Mining, Patter Detection, Acturial, Actuary, Long Term Disability, disability, claims data model sample, fraud detection, probablility

Disability Insurance Pricing
Better Analysis For Improved Pricing Accuracy

Advanced pattern detection

The Claim Analytics pricing approach harnesses advanced pattern-detection tools to identify and quantify, in simultaneity, complex relationships among multiple claim factors : age, gender, elim period, industry, region, salary, benefit, partial and residual benefits, and so on.

We build models to predict both (i) expected incidence rates and (ii) expected claim durations.

The same pattern-detection tools used by Claim Analytics are the tools of choice for many of the world’s toughest and most complex applications – credit card fraud detection, consumer buying prediction, weather forecasting, and taxpayer profiling.

Only a decade ago, this type of analysis was impractical in the business world. The data was not easily accessible. The tools were undeveloped. The applications had not been created. What a difference a decade makes.

Claimant-specific reserves

The Claim Analytics pricing approach incorporates claimant-specific reserves for each open claim.

The claimant-specific reserves are based on termination rates for each open claim, determined by the particular characteristics of that claimant, including information such as:

  • primary diagnosis
  • secondary diagnosis
  • CID date
  • region
  • occupation.

With these more precise and more accurate estimates of the costs of existing claims, we are better able to accurately predict the costs of future claims, leading to better pricing.

Disability Pricing

Download Document: 

Keywords: disability, Pattern Detection

Other products and services from Claim Analytics


claim scoring

Claim scoring uses advanced pattern detection technology to provide a numeric measurement of the likelihood of return to work of a disability claim. This accurate and objective measurement of disability or workers compensation claims enables the optimizing of all claim management resources. Forecasting Return to Work with Predictive Modeling By Barry Senensky and Jonathan Polon.



Traditional methodologies are constrained by their inability to manage more than a very limited set of claim differentiators: at best age, gender, elim period and one or two others. The Claim Analytics approach is to apply advanced predictive modeling techniques to determine precise, claimant-specific termination rates. This methodology results in reserves for each claimant that reflect that claimant’s true probability of terminating.


claim approval

The model was built by quantifying patterns in historical approval decisions and applying this logic to score newly reported claims on the likelihood that they would be approved based on an insurance companies existing practices. A score of 2 will indicate that eligibility and compliance to the duration guidelines need to be checked and then the claim can be approved.


fraud detection

Our technology goes beyond traditional rules-based approaches By comparing each claim to every other claim, and each practitioner to every other practitioner, our technology goes beyond traditional rules-based approaches to fraud detection. The claim history of each provider is compared to every other provider of the same specialty and outlier are quickly and easily identified.