making a quantitative case for ubi · simple anti-selection example 8 all values are hypothetical...

Making a Quantitative

Case for UBI

March 10, 2015

1 © Insurance Services Office, Inc., 2015

CAS Antitrust Notice • The Casualty Actuarial Society is committed to adhering strictly

to the letter and spirit of the antitrust laws. Seminars conducted under the auspices of the CAS are designed solely to provide a forum for the expression of various points of view on topics described in the programs or agendas for such meetings.

• Under no circumstances shall CAS seminars be used as a means for competing companies or firms to reach any understanding – expressed or implied – that restricts competition or in any way impairs the ability of members to exercise independent business judgment regarding matters affecting competition.

• It is the responsibility of all seminar participants to be aware of antitrust regulations, to prevent any written or verbal discussions that appear to violate these laws, and to adhere in every respect to the CAS antitrust compliance policy.

© Insurance Services Office, Inc., 2015

ROI and “the fallacy of planning”


Simulation: not just for actuaries

Recent examples:

• Ridesharing route optimization

• Autonomous vehicle decision calibration

• Cyber attack preparedness

• Particle collision research

• Super bowl predictions


Simulating the ROI on UBI

5

ROI

Selection

Driving

Improve-

ment

Ancillary

Revenue

vs. Cost

Savings

Reunder

-writing

Technology

Incentives

and Rewards

Analytics and

Models

Logistics

Partners and

Services

Elasticity

and Cost

Mix of

Business

Competitive

Landscape

Regulation

Distribution


Scoping the opportunity

6

10.4%

switch 12.6%

shop

then

stay

Source: “Fewer customers are shopping for auto insurance; however, nearly

one-half of those who do switch auto insurers”

http://www.jdpower.com/sites/default/files/2013060_insurance_shopping_study.pdf

What about

this 77%?

Every year in the U.S. …




Estimating components of ROI

7

Example for policyholders enrolled in year 1 of UBI program:

Positive

Selection

Benefits = ∑

Average

New

Business

Pure

Premium

UBI

Replace-

ment

Pure

Premium i

-

i = 1

N = # of

UBI pol-

icyholders

( 1 + discount rate ) j

∑ j = 1

P = Pred-

icted

Lapse


Simple anti-selection example

8

All values are hypothetical and illustrative. In the example, policyholders

switch to insurers with UBI if they can find a rate 25% lower.

Avg Pure Loss

Year Rate Danny DJ Michelle Jesse Joey Prem Ratio

1 800 228 423 520 618 813 520 65%

2 800 X 423 520 618 813 593 74%

3 913 X X 520 618 813 650 71%

4 1000 X X X 618 813 715 72%

5 1100 X X X 618 813 715 65%

884 611 69%


What more do we need to know?

9

0% 50% -50%

Dongle

Smartphone

OEM Equipment High

revenue

share

Low

revenue

share

High data

capture

device

Low data

capture

device

Intense

software

development

Basic

software

development

Hypothetical max/min spend scenarios by supporting technology

Five year annualized return on investment (ROI) © Insurance Services Office, Inc., 2015

Example of inter-relationships

10

Stronger data

collection

More capable

models

More accurate

feedback

More accurate

rating

Stronger

learning effects

Stronger

selection effects

Perceived

over-reach

Higher tech

Spending

Tough to meet

opt-in goals

Weaker

selection effects

More device

rotations Weaker

learning effects


11

How much does the model matter

-75.0%

-50.0%

-25.0%

0.0%

25.0%

50.0%

1 2 3 4 5 6

Constant Learning

-75.0%

-50.0%

-25.0%

0.0%

25.0%

50.0%

1 2 3 4 5 6

Constant Learning

-75.0%

-50.0%

-25.0%

0.0%

25.0%

50.0%

1 2 3 4 5 6

Constant Learning Graduated Learning

Hypothetical

Five Year

Annualized ROI

Model Power

(High Tertile ÷

Lower Tertile )

“Common Dongle / Book of Business” Assumption Set

• Approximately industry average premiums / expenses

• $100 hardware, $5 monthly wireless

• Three year useful life

• Three vehicles per year

• 10% annual cost reductions


Differentiation by rating variable

12

Combined Single Limit Liability (CSLL) rating factors derived from ISO Personal Vehicle

Manual (PVM). Insurance Score factor estimate based on preliminary ISO research and

subject to change before publication.

Max ÷

Rating Variable Min

Operator Age 3.36

Estimated Annual Mileage 1.90

Insurance Score 1.86

Number of Accidents at Fault 1.75

Vehicle Use 1.53


Sample UBI model performance

0.000

0.500

1.000

1.500

2.000

2.500

3.000

1 2 3 4-5 6 7 8 9 10

Loss

Rat

io In

de

x

Safety Scoring Decile (least risky to most risky)

Top two deciles: loss ratio 2.25 times average

Bottom two deciles: 20% of average loss ratio

Source: >800 personal lines vehicles

Validation performed on vehicles used in model derivation, but holdout driving period.

© I

nsu

ran

ce

Se

rvic

es O

ffic

e, In

c.,

20

15

Potential communication breakdown

@[Insurer] I’ve used #[Telematics

Product] for 6 mts. Evrytime I applied

my brakes, or drv in traffic I was

dinged. Its not calibrated for metro.

-BuyfromKMJ

According to [Insurer] [Telematics

Product], I am an A driver in my

Jeep, and a C driver in my car.

Ridiculous. Sent the [darn] things

back. #epicfail - wildannie1969

@[Insurer] [Telematics Product] is

one of the worst devices ever

invented. False hard brakes

CONSTANTLY in icy weather while

accelerating. Constantly. -

TimothyJohnWI

How does this work @[Insurer] I

pressed breaks early to avoid

running a yellow light BUT your

#[Telematics Product] beeped at me.

Should I have ran it? -_ylimE


Example of learning

15

0

10

20

30

40

50

60

70

0 5 10 15 20

Initially Safest Initially Average Initially Riskiest

ISO

Safe

ty S

core

Weeks of Driving

UBI Score by Week of Driving

Incre

asin

g R

isk

Source: Sample of over 1,000 private passenger vehicles observed in late 2014


Teaching considerations

• Time and distance halo effects

• Feedback loops and Garden Grove case

• Verbal vs. tonal vs. visual feedback

• Driving habits vs. thinking habits


The economics of teen driver programs

17

-40.00%

-30.00%

-20.00%

-10.00%

0.00%

10.00%

20.00%

30.00%

40.00%

0.25 0.75 1.25 1.75 2.25

Average premium per vehicle (relative to

approximate industry average)

Five Year

Annualized

Return on

Investment (ROI)

Assumes common dongle cost structure, device deployment to three

vehicles per year, and 3x model power.

Projected ROI by Average Premium of

Vehicle Enrolled in UBI Program


Ancillary benefits of teen driver UBI

• Strong desire for product among parents

• More teachable participants

• Higher lifetime value possibilities

• More likely to promote on social


Monte Carlo simulation

19

0%

1%

2%

3%

4%

5%

6%

7%

8%

9%

Five year return on investment (ROI)

Assumes common dongle cost structure, device deployment to three

vehicles per year in typical book, and 3x model power.

Perc

enta

ge o

f S

imula

tions


Decision time

• Decision-making shouldn’t overlook

costs of delay or inaction

• Different technologies offer different

cost and revenue models

• Stronger predictions enable stronger

selection and teaching effects

• Marketing strategy should consider

relative technological costs


Questions?

No part of this presentation may be copied or redistributed without the

prior written consent of ISO. This material was used exclusively as an

exhibit to an oral presentation. It may not be, nor should it be relied

upon as reflecting, a complete record of the discussion..


making a quantitative case for ubi · simple anti-selection example 8 all values are hypothetical...

Documents