High Tech Processing

Download Report

Transcript High Tech Processing

High Tech Processing:
From Application to Policy Issue
Presented by Keith Hoeffner
February 16, 2011
Agenda
High Tech Processing – present challenges
Electronification of application fulfillment
Wide Open Possibilities Available Now
What’s next?
Process Challenges
Obtaining a complete and legible application
 Part 1
 Part 2
Cycle Time






Paramedical exam and lab
EKG scan
APS
Piece meal delivery
Discretionary requirements
30+ days
Legal and compliance adoption of
process improvements
Life Insurance Application Process
Don’t Be Trapped In A Paradigm
Wide Open Possibilities
Straight through processing
Plus data mining
Real-time transactions
Workflow improvements
Predictive modeling
Straight Through Processing
Pre-App
E-Sign
Application
UW
Requirements
Ordered
Drop Ticket
Exam
Scheduled
Data, Results
Delivered
Part 1
Interview
Part 2
Interview
Policy
Underwritten
(multiple
carriers)
End-to-End Life Insurance Application Workflow
Reduces Cycle Time by 14+ Days
What do we do with the data?
Automated underwriting
Import application data directly into underwriting
system – eliminate data entry
Workflow tools and business rules order medical
requirements
Rules based decisions
Routing of more complex cases to the right
underwriter at the right time
Paving the Cow Path
Nothing wrong with paving the cow path when the
cow path indicates a desire line that leads to process
efficiency.
Until you are ready for the super highway
How Do You Make a Difference?
Stage 1
Integrate external data into straight through process
 Prescription history
 MIB
 MVR
Eliminate contradictions
Take an underwriting file from IGO to IRGO
In REALLY Good Order
How?
The Advent of Real-Time Transactions
Real-time transactions are
made possible through
Web Services – a method of communication
between two electronic devices over the web
 Web services describes
a standardized way of
integrating Web-based
applications using
− UDDI to list the services
− WSDL to describe the
services
− SOAP to transfer the
data over the Internet
− XML to tag the data
Real-Time Transactions
Web services
 Used primarily as a means for businesses to



communicate with each other and with clients
Web services allow organizations to communicate data
without intimate knowledge of each other's IT systems
behind the firewall
Web services allow different applications from different
sources to communicate with each other without timeconsuming custom coding
Because all communication is in XML, Web services are
not tied to any one operating system or programming
language
Real-Time Transactions
Web services (continued)
 Java can talk with Perl, Windows applications can talk


with UNIX applications, etc.
Web services do not require the use of browsers or HTML
Web services are sometimes called application services
How Do You Make More of a Difference?
Stage 2
Process improvements

Expand the data set
− New field technology to capture more data
• Digital ECG’s
• Laptop

Improve workflow
− Real-time exam scheduling
− Voice signatures and e-signatures
− Laptop and call center integration
How Do You Really Make a Difference?
Stage 3
Predictive modeling – the next step beyond automated
underwriting
What is predictive modeling?
 Predictive modeling is the process by which a model is


created or chosen to try to best predict the probability of
an outcome
In many cases the model is chosen on the basis of
detection theory to try to guess the probability of an
outcome given a set amount of input data
Discerning between information bearing data and noise
Look very closely at the next
animated slide…
Which way was the woman
whirling?
How To Take It To The Next Level
MIB, prescription history, MVR
Relevant lifestyle data
 Exercise
 Diet
Demographic: population density, medical care
index
Personal: gender, age, occupation, education,
marital status
Finances: assets, income, credit history
How do you mine this data?
Consumer Data – Grocery Loyalty Card
Age and gender
Tobacco use
Alcohol use
Occupation
Neighborhood
Hobbies and interests
ATM use (noise or informational data)
Brands (or noise or more informational data)
What Do You Do With It?
Correlations? Cause and effect?






Sea temperatures and hurricane frequency
Education and earnings
Height and weight
Marital status and mortality
Type of neighborhood and longevity
Lifestyle and mortality
Predictive Underwriting – Paul Hately, Swiss Re
Predictive Underwriting – Paul Hately, Swiss Re
Maybe I’m just not smart enough
to figure all this out. Are you?
Olny srmat poelpe can raed this. I cdnuolt blveiee
that I cluod aulaclty uesdnatnrd what I was rdanieg.
The phaonmneal pweor of the hmuan mnid,
aoccdrnig to a rscheearch at Cmabrigde Uinervtisy,
it deosn't mttaer in what oredr the ltteers in a word
are, the olny iprmoatnt tihng is that the first and last
ltteer be in the rghit pclae. The rset can be a taotl
mses and you can still raed it wouthit a
porbelm. This is bcuseae the huamn mnid deos not
raed ervey lteter by istlef, but the word as a
wlohe. Amzanig huh? yaeh and I awlyas tghuhot
slpeling was ipmorantt! if you can raed this psas
it on!!
Current Predictive Modeling Activity
BioSignia – Mortality Assessment Technology (MAT)
ExamOne RiskIQ
CRL – SmartScore
Heritage Labs – Risk Score
Challenges of Predictive Underwriting
Data may be predictive but also meet public
acceptance thresholds and legal requirements
Anti-selection by agents
Reinsurance attitudes
Pricing – risk classification comparisons to traditional
underwriting
Benefits of Predictive Underwriting
Improved underwriting efficiency…and much, much
more
 Consumer, demographic, personal and financial data



less expensive and more readily available than
traditional underwriting tests
Smarter APS ordering
Fast – decisions in minutes or hours vs. weeks or months
Cheap – data is cheap, knowing how to use it may be
another story
Premium growth – increased sales
 Reduced process time increases placement ratios
 Attract new producers
 Target marketing – consumer data
Conclusion
Evolution not revolution
Continue to make incremental process improvements
within the parameters of your organization
Be cautious to avoid anti-selection pitfalls
Continue to stay tuned into advancements by
reinsurers
 RGA Re
 Swiss Re
The End!
Additional reference: Predictive
Modeling Comes to Life by Bary T.
Ciardiello, David W. McLeroy