gi analytics field guide - actuaries
TRANSCRIPT
GI Analytics Field GuideA roam over the data analytics countryside
Amanda Aitken, Irene Chen, Tanya Wood,
John Connor and Jonathan Cohen
This presentation has been prepared for the 2016 General Insurance Seminar.The Institute Council wishes it to be understood that opinions put forward herein are not necessarily
those of the Institute and the Council is not responsible for those opinions.
Agenda
• Introduction
• Demo of wiki
• Field Guide Content– Personal Injuries
– Natural Hazards
– Performance Monitoring
– Lenders’ Mortgage Insurance
– Short Tail Pricing
• Conclusion
Introduction
Meet The Working Group
Personal
Injuries
Short Tail
Pricing
Lenders’
Mortgage
Natural
Hazards
Performance
Monitoring
Capital
www.m8asolutions.com/wiki/index.php/Main_Page
Demo of wiki
Personal Injuries
Natural Perils
Bushfire risk profiling: distance to bush
Flood risk profiling in Bundaberg, QLD: distance to river
Flood risk profiling in Bundaberg, QLD: difference in elevation
Performance Monitoring
Adding Insight
to Business
Operations
Issues to consider:
• Management of Data
• Production of Reports
• Embedded Analysis
• Visualisation tools
• User interpretation of analysis
Lenders Mortgage Insurance
High risk regions
Reinsurance optimisation
Idiosyncratic risk -
Loan characteristics
Systematic risk - State
of the economy Economic Scenario Generator as a key input
Internal, census and
external property data
Spatial smoothing to
identify high risk
regions
• Model scoring
• Model updates
• Control individual price
changes
• Available tools and
data
• Ensure that each
predictor adds value in
excess of its cost!
• Systems
• Distribution
• Lead time for pricing
changes
• Legalese
Short tail pricing
Get started
• Business objectives
• Market competition
• Staff capacity
• Regulatory requirements
Understand the constraints
Make sure you can use itBuild it out
“We charge 2% of Sum
Insured to everyone”
There is a spectrum of possible
pricing structures…
No nonsense
Whizz bang
“Our prices update
dynamically based on
customer and market
actions”
“We have 200 features
of each customer and
we use them”
… so we want to build a practical cheat sheet to
help find the right one for the job
(We’ve made a start!)
Conclusion
Lots of analytics opportunities that can add value to general insurers
Know how to validate data
Know the business
Able to highlight and embed assumptions
Take a long term view
Bound by professional standards
As actuaries, we should position ourselves to lead the way, leveraging our
differentiating strengths
We’d love for you to get involved in building the wiki too!
Add to existing topics, create new topics
and join in the discussion
http://www.m8asolutions.com/wiki/index.php/Main_Page
