Insurance Telematics: Big Data, Big Potential, Big Headache Dave Huber, President Kairos Solutions IFSUG March 2012
Big Data 2
ne of the few products whose price is set before costs are known Known costs Unknown costs Loss adjustment expense Pure premium (freq x sev) perations Bodily injury Advertising Comp & Collision Underwriting Regulatory Commissions Trends Known costs Unknown costs Premium Data drives insurance decisions 3
Pricing sophistication is a competitive advantage and depends on data analytics Granularity The number of pricing cells per question or variable Age: 16-19, 20-25, 26-30 vs. 16, 17, 18, 19. Dispersion The range of rates for each of the variables $450-$900 vs. $225-$1375 Interactions The lift when combining variables Vehicle symbol & territory pickups in suburbs Variables New questions and/or external data Credit, occupation, prior limits 4
Insurers generally use the same data to price $1000 $1000 31 M S Speed 4 wn Y 611 YMM Age Gender Marital status Violations Points Homeowner Prior insurance Credit Vehicle 31 M S Speed 4 wn Y 611 YMM These drivers look like Pure Premium Carbon Copies and are priced identically 5
But imagine knowing something about drivers that no one else knows $800 $1200 31 M S Speed 4 wn Y 611 YMM 10,651 4.9 Age Gender Marital status Violations Points Homeowner Prior insurance Credit Vehicle Verified Annual Miles Trips per day 31 M S Speed 4 wn Y 611 YMM 13,182 6.1 So they re NT Pure Premium Carbon Copies after all and they deserve a different price 6
Usage-Based Insurance is all about segmentation & pricing How, when & where you drive Driving data s not readily available & expensive to collect Need a lot of driving data Beyond insurers core competency Insurers would really like a driving score 7
The pricing advantage of UBI data is big Granularity The number of pricing cells per question or variable Age: 16-19, 20-25, 26-30 vs. 16, 17, 18, 19. Self-reported mileage buckets vs. verified continuous mileage Variables New questions and/or external data Credit, occupation, prior limits How, when & where, self-selection, personal driving score akin to a credit score Interactions The lift when combining variables Vehicle symbol & territory pickups in suburbs Miles x time of day, frequency & magnitude of speed changes, speed x traffic Dispersion The range of rates for each of the variables $450-$900 vs. $225-$1375 Personalized pricing 8
Where does driving data come from? BD data loggers EM embedded telematics Smartphone apps 9
So what does when, where & how look like? Time-stamped trip start/stop, engine on/off BD - vehicle speed every second GPS - lat, long & heading every second Accelerometer 3 axis acceleration How big is Big Data? 5,000 GPS-enabled devices 8MM journeys & 15B journey points 20 million new rows of data daily 10
How might all this Big Data show up? Annual mileage Avg trip duration Avg trip length Trips per day Trips per time of day Journeys Miles by time of day Miles by day of week Weekdays Weekends Miles in speed bands Time in speed bands Average speed Trip regularity (miles) Trip regularity (time) Aggressive acceleration per 100 miles Aggressive braking per 100 miles Road type Relative speed Miles in territory Drive time in territory Idle time in territory Cornering Lateral acceleration Rolling stops Self-selection Lane changes Acceleration events in speed bands Braking events in speed bands Frequency of speed changes Magnitude of speed changes Commuter profile Errand-runner profile Coffee drinkers YMM relativities nstar subscription Cruise control Driver score Driver footprint Left turns Speed variation Trip type (speed vs time) Territory by time of day Holiday driving School zone Violations by trip type Trip radius Student profile Intersections Turn signal Seat belt Lights / wipers Vehicle maintenance Time between trips/journeys Congestion index Summer car Texting & phone use 11
Big Potential 12
Growth depends on acquisition & retention 13
Driving data colors the opportunity 14
But insurers without UBI are color blind 15
UBI book attracts preferred drivers who are accurately priced 16
Insurers without UBI are left with a book that looks like this to them 17
But in reality behaves like this 18
Big Headache 19
UBI has a lot of moving parts 20
Data-related issues are only part 21
Insurers are good at some of the stuff, but their core competencies are limited 22
Telematics Service Providers bring expertise to the table and have a role to play 23
Insurers and TSPs have collaborative opportunities to work together 24
Seems like there s an opportunity for SAS somewhere in the UBI puzzle 25
Insurance Telematics: Big Data, Big Potential, Big Headache Any big, but easy questions? Dave Huber Kairos Solutions 415-308-5408 26