Renewing LTD Using Data Mining Techniques Canadian Institute of Actuaries November 10, 2005

1
Renewing LTD Using Data Mining
TechniquesCanadian Institute of
ActuariesNovember 10, 2005
Barry Senensky FCIA www.claimanalytics.com
2
Agenda

• Data mining
• Claims scoring
• Using claim scoring to develop LTD reserve
  termination assumptions

3
Data MiningDefined

• Extraction of previously unknown information from
  large data sets or databases
• Finding and quantifying of hidden patterns and
  trends in databases

4
Data Mining Applications

• Used extensively in industry
• Credit card and tax fraud detection
• Credit scoring
• Weather prediction
• Handwriting to text conversion
• Many, many other applications

5
Data Mining Tools

• CART
• 2. Neural Networks
• 3. Genetic Algorithms

Filter.
Identifies factors with
greatest impact.
Optimization tools
6
Neural Networks / Genetic AlgorithmsHow they
learn

• Model is presented with data sample with known
  outcomes
• Model predicts result, then compares it to actual
  outcome
• Model parameters are changed to better
  approximate the sample
• Over and over again.

7
Claims Scoring

• Claims are scored from 1 to 10.
• Scores show likelihood of return to work within a
  given timeframe.
• Scores are calibrated
• score of 1 indicates 0 10 chance of recovery
  within given timeframe, score of 2 indicates 10
  20 chance of recovery within given timeframe,
  and so on.

J. Spratt Score 4 452135
8
Scoring Report
Q.P.





9
Five steps to developing LTD termination rates
for Dave using claim scoring
Dave
10
Developing termination rates for Dave
About Dave
11
Developing termination rates for Dave
Daves claim scores
Likelihood of RTW ()
12
Developing termination rates for Dave
Step One Get Cumulative RTW Probabilities

• cumulative RTW Probabilities, 1-24 Months after
  EP
• expressed as

13
Developing termination rates for Dave
Step Two Interpolate between months

• choose uniform distribution, constant force or
  Balducci
• here, used uniform distribution
• expressed as

14
Developing termination rates for Dave
Step Three Get mortality rates

• Canadian Group LTD experience /1000 shown here
• alternative is company experience
• may want to make adjustments, e.g. improvement
  from mid-point of study

15
Step Four Convert cumulative RTW probabilities to
month-to-month RTW rates
Developing termination rates for Dave
of claimants who will recover in period. 
TM cumulative RTW - LM cumulative RTW
1 - LM cumulative RTW - LM cumulative death rate
of claimants still on claim at start of period.
 
16

• Step Five
• Calculate Termination Rates
• Termination rate recovery rate mortality rate

Developing termination rates for Dave
17
What to do after 24 months

• Produce scores for 36 months, then use
  traditional methods thereafter
• Produce scores for all future terms

18
Credibility

• Significant benefits over traditional methods
• Rates are based on internal experience
• Data mining offers advantages over table of
  claims analysis

19
Credibility

• Testing the model
• Normally use back-testing to confirm fit of model

20
Back-testing the Scoring Model
21
Benefits

• More appropriate reserve for each claim, avoid
  averages of averages
• Aligned with claim management practices
• Facilitates repricing / renewal
• Earlier recognition of changes in trends and
  experience

22
Summary
Claim scoring offers a new and innovative way of
setting LTD termination rates that results in a
more appropriate reserve for each claim.