Discovery Through Statistics Claim Analytics Group Disability Reservin Group Disability Reserving Unleash the Power of the 21 Unleash the Power of the 21 st st Century Century Canadian Canadian Institute of Actuaries Institute of Actuaries June 29 2006 June 29 2006 Barry Senensky FCIA Barry Senensky FCIA www.claimanalytics.com www.claimanalytics.com
31
Embed
Discovery Through Statistics Claim Analytics Group Disability Reserving Unleash the Power of the 21 st Century Canadian Institute of Actuaries June 29.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Discovery Through Statistics
Claim Analytics
Group Disability ReservingGroup Disability ReservingUnleash the Power of the 21Unleash the Power of the 21stst Century Century
Canadian Canadian Institute of ActuariesInstitute of ActuariesJune 29 2006June 29 2006
• Access to large databases of historic information
Evolution of Reserve CalculationsEvolution of Reserve Calculations
Discovery Through Statistics
Claim Analytics
What Have We Accomplished?What Have We Accomplished?
Tremendous progress made possible by evolution of computer power
Calculations now explicit and seriatim Scenarios sensitivity-tested to better
evaluate risk Experience studies more frequent
Discovery Through Statistics
Claim Analytics
What do we still need to do?What do we still need to do?Group Disability ReservingGroup Disability Reserving
Frequent and comprehensive experience informationo Studies at least annuallyo Ability for user to slice-and-dice information
Information electronically provided to users
Why?o More appropriate, up-to-date experience information
Obstacleso Lack of priority
Discovery Through Statistics
Claim Analytics
Need key predictive factors of recovery, particularly diagnosis, but also Quebec, monthly benefit, tax status, reporting lag, incorporated into reserve calculation
Why?
o More appropriate reserve for each claim o Immediately capture business mix changeso Eliminate cherry picking at quarter-endso Align with claim management practiceso More understandable to management o Relevant for experience rating situations
Obstacleso Lack of training in predictive modeling o How do you do it? (There can be thousands of diagnoses)o Cost to implement
What do we still need to do?What do we still need to do?Group Disability ReservingGroup Disability Reserving
Discovery Through Statistics
Claim Analytics
How do we build diagnosis into How do we build diagnosis into reserve calculations?reserve calculations?
Discovery Through Statistics
Claim Analytics
o Classify each diagnosis into a set of categories, based on likelihood and time to recovery
o Develop unique termination rates for each category
Weaknesses: • Labour-intensive• Subjective• Data credibility issues
Method 1
Building diagnosis into reserve calculationsBuilding diagnosis into reserve calculations
Discovery Through Statistics
Claim Analytics
Building diagnosis into reserve calculationsBuilding diagnosis into reserve calculations
o Use predictive modeling techniques to produce scores that equate to probabilities of recovery or termination
o Calculate reserves directly, using scores
SOA paper outlines methodology for creating scores
Scores are proven and credible
Method 2
Discovery Through Statistics
Claim Analytics
Using Predictive Modeling Using Predictive Modeling to Calculate Reservesto Calculate Reserves
Discovery Through Statistics
Claim Analytics
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
ClaimsClaims ScoringScoring
J. Loe Score: 6# 452009
P. Chang Score: 8# 451156
Discovery Through Statistics
Claim Analytics
…
…
…
…
…
Claim # Elim Diagnosis Sex Age Benefit (Other ) 6M 24M
451122 119 Depression Reactive (Prolonged)
M 42 1411 7 10
452024 364 Tear Medial Meniscus (Knee)
M 47 2500 4 7
452141 180 Fibromyalgia F 37 3899 6 6
452338 180 Major Depressive Disorder
F 35 1773 6 8
452341 119 Lumbar Disc Degen/Disease
M 42 1150 2 5
452494 210 Herniated Disc Acute F 59 3564.9 2 2
ScoringScoring ReportReport
Q.P.
Discovery Through Statistics
Claim Analytics
Five steps to developing Five steps to developing LTD termination rates for DaveLTD termination rates for Dave
using claim scoringusing claim scoring
Dave
Discovery Through Statistics
Claim Analytics
About Dave
Sex Male
Age 44
QP 90 days
Diagnosis Osteoarthritis
Developing termination Developing termination rates for Daverates for Dave