Neil Versel Information Week November 15 2011 Shipi Kankane Prashanth Nakirekommula Applying analytics and risk management capabilities to health insurance through LexisNexis data platforms ID: 504624
Download Presentation The PPT/PDF document "Data Mining Snares Health Insurance Frau..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Data Mining Snares Health Insurance FraudNeil Versel ,Information Week, November 15, 2011
Shipi
Kankane
Prashanth
NakirekommulaSlide2
Applying analytics and risk- management capabilities to health insurance through LexisNexis data platforms. Databases on 250 million people in the U.S. sampled from 35 billion public records.Data analysis using its supercomputer platform, which is built on top of open-source platform (High Performance Computing Cluster)Allows for fast queries of "massive amounts of big data.”The news Slide3
LexisNexis HealthCare SolutionEarlier Situation: Pay and Chase model - insufficient and unsustainableCurrent Solution: Proactive - identifies and mitigates fraud throughout business workflowIdentify fraud patterns and risk indicators as they emerge.Slide4
Predictive ModelingMetricsScoresDetect inherent risksTraditional Method:Single claimClaim EditNo pattern identificationSlide5
Definition: Predictive Analysis translates data into descriptive or predictive models using various forms of statistical analysis techniques Classification and Regression Trees (CART) Chi Square Automatic Interaction Detection (CHAID) . Linear and logistic regression models Analysis of variance Discriminate analysis.Predictive Analysis Slide6
Predictive AnalysisSlide7
Benefits Early detection of fraud, waste and abusePrioritized results with fewer false positivesAlerts concerning adverse changes in the status of individuals or entitiesConsistent control over risk, quality and costs using automated screening and monitoringLower claims losses, better financial management than traditional “post-payment only” methodsSlide8
Understand your data – Patient demographics, Hospital Information etc.Determine your population makeup – Sampling issues, representativenessDiscover relationships in your data – Relations between various variables identified in Step 1Build a model – Rule induction and based on step 3Use model against actual records – Test for predictive powerIdentify anomalies – OutliersIBM SPSS ModelerSlide9
SAS datamining tool – tree based model , multianalytics approachIBM SPSS modeler – rule inductionOther Vendors Slide10
Take Away MessageSlide11
Neil Versel , Data Mining Snares Health Insurance Fraud, InformationWeek , November 15 ,2011LexisNexis® Health Care Solutions for Fraud, Waste and Abuse Prevention retrieved from lexisnexis.comHPCC Systems (www.hpccsystems.com)IBM Software Business Analytics, IBM Corporation, May 2011References