© 2008 megaputer intelligence inc. subrogation prediction through text mining and data modeling...

39
© 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence www.megaputer.com

Upload: devon-burham

Post on 01-Apr-2015

227 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Subrogation Prediction Through Text Mining and Data Modeling

Sergei Ananyan, Ph.D.Megaputer Intelligencewww.megaputer.com

Page 2: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Why Subrogating?

• While only a few percent of cases have subrogation potential, significant amounts of money can be recovered

• Estimates: Missed subro opportunities in USA ~ $15Billion annually

• Efficient subrogations facilitate in keeping insurance premiums low, providing an extra competitive edge

Page 3: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Challenges of Subrogation• Overwhelming volume of claims:

– Over 5 million reported workplace injuries in the USA annually– Over 6 million auto insurance claims in the USA annually

• Subrogation opportunities comprise only a few percent of all claims

• Subro decisions involve manual analysis of textual notes in claims

• Thorough investigations can be lengthy and costly

• Missed subrogation opportunities can be even more costly

• Subro decisions should be made soon after the accident. Relevant evidence may disappear quickly.

Page 4: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Who makes a subro decision?

Page 5: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Traditional Way: Adjusters• Individual Adjusters determine subrogation cases

• Pros:– Subro decisions can be made at early stages of claim handling– Investigation can be conducted on the spot

• Cons:– Subrogation determination is at the bottom of a long list of actions

• Verifying coverage

• Determining compensation

• Approving payments

• Reporting

– Different experience of adjusters: no consistency across organization– Either the lack of formal rules or a set of rules that is too rigid to determine

subrogation potential of many cases– Looking for “a needle in a haystack”: easily overlooked

Page 6: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Traditional Way: Recovery Teams• Specialized Recovery Teams determine subrogation opportunities

• Pros– Highly trained professionals: better determination of opportunities– Consistency across the organization

• Cons– Small group of investigators: overloaded with large numbers of claims– Located remotely: need to coordinate efforts with local adjusters– Delays in starting investigations

Page 7: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Recovery Teams are Overloaded

Page 8: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Subrogation Prediction Objectives

• A perfect solution for subrogation prediction should be– Accurate– Automated– Objective– Consistent– Fast

Page 9: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

New Way: Automated Modeling

• New predictive modeling tools can identify subro opportunities

• They provide many benefits– Timely detect good new candidate claims for subrogation– Capture missed opportunities throughout closed cases– Focus attention of investigators on cases with high potential– Eliminate wasted time and efforts– Standardize subrogation prediction practice across the enterprise– Enhance customer satisfaction

Page 10: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Modeling and Text Mining

• Knowledge discovery tools for business users• Easy-to-understand actionable results

Data OverloadUseful Knowledge

Page 11: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

What is Data Modeling?

• Computer models learn from historical data and predict outcomes of future situations

• Models are developed through training on data with known outcomes

• Training is based on machine learning and statistical algorithms

• The Megaputer solution PolyAnalyst™ for Subrogation Prediction offers a selection of modeling algorithms:

– Decision Trees– Neural Networks– CHAID– Bayesian Networks– Random Forest

• Best model can be selected automatically

• Developed models are used for scoring new data to predict:– Probability of the subrogation success– Potential recovered amount

Page 12: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Training and Applying the Model

• Model Training:– Modeling is carried out on data collected from claim forms and notes– Successful past subrogation cases are considered as positive examples– “No subrogation” cases are negative examples– A model learns combinations of features determining positive cases– Another model predicts the amount of possible subrogation– The developed model is stored for future use

• Model Application– Models are applied to new data to produce scores– Calculate:

• Subrogation probability

• Subrogation amount

– Claims with the highest scores on these two attributes are presented for investigation by a human

Page 13: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Investigations involve data analysis

Data Analyst

Visual analytic scenario

Decision Maker

Interactive up-to-date reports

Page 14: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Behind the Scenes

Page 15: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Output: Subrogation Prediction

• Probability of the subrogation success

• Estimated recovery amount

Page 16: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Data Integration

Page 17: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Data Cleansing

Page 18: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Aggregation – keys and attributes

Page 19: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Aggregations - measures

Page 20: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Derivative Attributes

Page 21: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Complications of Text Analysis• The need to analyze free text notes further complicates things

• Statistical tools are good at processing structured data, but not text

• Human analysts had to read text notes to extract relevant features

Page 22: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Text Mining Technology

• Text Mining is an automated process of analyzing text to extract information from it for particular purposes

• Text Mining is different from traditional search technology:– In search, the user is typically looking for something that is already known and

has been written by someone else– Text Mining involves pushing aside irrelevant material in order to extract relevant

information

• Text Mining extracts relevant features from natural language notes. These features are included in modeling.

Page 23: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Typical Text Mining Tasks

• Categorization

• Feature and entity extraction

• Summarization

Page 24: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Complications of Text Analysis

• Typical textual descriptions– SLIPPED OFF BACK OFVAN LOADING TOOLS– PUSHED WHILE CONFRONTING AN ALLEGED SHOPLIFTER– TRIPPED ON A SHEET OF WIRE MESH & FELL ON PAKRING LOT– REACHING FOR PAKAGES ON BELT WHEN HE TRIPPED OVER

PAKAGES THAT WERE IN FRONT OF BELT AND FELL– EE WAS CUTTING ONIONS ON THE SLICER AND HE CUT OFF THE TIP

OF HIS RIGHT THUM– CLT WAS STRUCK ON HEAD WITH ICE IN THE FREEZER– EMP WAS WALKING BACK TO PKG CAR WHEN 2 DOGS BEGAN TO

CHASE HIM, HE RAN & SLIPPED ON STEPS OF PKG CAR– EE WAS USING A BAND SAW TO CUT IRON FOREIGN BODY

ENTERED LT EYE

Page 25: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Intelligent Spell-Checking

Page 26: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Categorization: V2 rear ended V1

Key points of the claim

Page 27: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Categorization: policy holder arrested

Key points of the claim

Page 28: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Domain-specific Dictionaries

Page 29: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Patterns related to Pain

Page 30: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Predicted Subro Probability for a Claim

Page 31: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Predicted Subro Amount for a Claim

Page 32: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

PolyAnalyst Subro Prediction flow

Text Mining

ModelingSubrogation

Model

Historical claims data

Subrogation prediction

New claim

ExtractedFeatures

Page 33: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Touch Points for Modeling

• First Report of Incident– Detect subro opportunities, while evidence is still available– Focus efforts only on claims that have good subro potential– Perform timely and thorough investigations

• Retrospective Analysis of Claims– Check closed and still open claims– Identify missed subro opportunities– Pursue recovery whenever still possible

Page 34: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

First Report of Incident (work comp)

• Available data– Date– Injury Type– Body part injured– Textual description of the incident

• Build models based on historical data

• Use a pre-built model to score new claims

Page 35: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Retrospective Claims Analysis

• Extra data (new)– Claim notes– Financial results– Applicable legislation, Arbitration notices, etc.

• Build models based on historical examples

• Discover missed subrogation opportunities

Page 36: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

PolyAnalyst Benefits

• Dramatic time and cost reduction

• Increase in quality and speed of the analysis

• Objective and uniform data-driven analysis

• Discovery of even unexpected issues suggested by data

• Automated monitoring of known problems

• Timely discovery of newly developing issues

• Utilization of 100% of available data: structured and text

• Up-to-date reports for executives

• Easy to use and to maintain solution

Page 37: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Data and Text Mining in Insurance

• Fraud Detection

• Subrogation Prediction

• Database Marketing– Response Prediction– Cross-sell Analysis– Market Segmentation

• Text Analysis– Call Center transcripts analysis– Survey analysis– Competitive intelligence– Compliance analysis

Page 38: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Select Customers

Government

Insurance

Financial

High Tech

Pharmaceutical

Marketing

Manufacturing

Page 39: © 2008 Megaputer Intelligence Inc. Subrogation Prediction Through Text Mining and Data Modeling Sergei Ananyan, Ph.D. Megaputer Intelligence

© 2008 Megaputer Intelligence Inc.

Contacting Megaputer

Call(812) 330-0110

or [email protected]

120 W Seventh Street, Suite 314Bloomington, IN 47404 USA