December 03, 2013

Usage-based insurance (UBI) has been around for a while – it began with Pay-As-You-Drive programs that gave drivers discounts on their insurance premiums for driving under a set number of miles. These soon developed into Pay-How-You-Drive programs, pioneered by Progressive, which track your driving habits and give you discounts for 'safe' driving.

In the traditional system, a consumer calls an insurance company, provide some basic information, and get a quote for auto insurance based on type of car, age, gender, marital status, location, driving history, and credit history of the customer. These attributes act as proxies for your auto risk, and the riskier you are the more likely you are to file a claim. These attributes allow an insurance firm to stack you up against the rest of population and see where you are likely to fall in terms of risk. They are playing a guessing game based on averages.

With UBI, the need for these best-guess proxies is gone. UBI allows a firm to snap a picture of an individual's specific risk profile, based on that individual's actual driving habits. UBI condenses the period of time under inspection to a few months, guaranteeing a much more relevant pool of information. In addition, it allows consumers to have control over their premiums.

Where does Big Data enter the picture? Well, this is going to be a lot of data to manage. A blog on edgewater.com notes that within a year of enrolling 1,000 average drivers on a UBI program, an insurance carrier must accommodate the transmission and storage of over 190 million data points.

[State Farm sees opportunity in home monitoring technologies]

Insurers will need to be able to make sense of this data via a model with predictive capabilities based on frequency of driving, hard braking, sharp turns, and a handful of other factors, to determine the optimal premium for each individual. The more data available, the more comprehensive the model and the analytics will be, and the more accurate the customer's risk profile will be.

The truth is, this attempt at more accurate mass-customization of premiums is still developing. By moving away from the use of proxies for risk and looking at individuals' driving habits & behaviors, companies are trying to give safe consumers the discounts they deserve, while developing better insights into those with high risk.

What does the future look like? Current UBI programs include Snapshot by Progressive, Drivewise by Allstate, TrueLane by Hartford, and Ingenie's 'Black-box' approach, which focuses solely on telematics-based insurance for young drivers. Although this is much more efficient than the traditional system of annual renewals, this is still not the UBI of true Big Data. Big Data and Big Data analytics-powered UBI based on real-time data has the potential to provide fully dynamic insurance pricing. Flexible algorithms for customer risk profiles coupled with the growing, and increasingly better understood, capabilities of Big Data paint a far more intriguing picture.

Phani Nagarjuna, Nuevora
Phani Nagarjuna, Nuevora

Imagine an insurance firm that could bill you daily and calculates your risk profile in real-time, as your driving data is captured. As an analogy, your utility company doesn't bill you for electricity ahead of the month – they calculate your bill based on changes in your power use. Why shouldn't this apply to auto insurance as well, where your insurance premium is calculated based on changes in your risk profile?

If you were to go on a vacation, and your car is sitting in your garage, your auto insurance should ideally be rock bottom, if not zero. The best dynamic pricing scheme would completely flip its risk calculations and, for that week-long vacation, base your insurance premium solely on the risk of your car getting vandalized or stolen while in your garage. This would exclusively take into consideration your specific neighborhood, the time of year, etc. As soon as you get back and turn on your car, the algorithm would intelligently decide which factors pose the greatest risk and calculate your insurance premium accordingly. Considering the trends toward more comprehensive data sets and better access, these algorithms could take into consideration weather forecasts, traffic, road deprivation and road-specific accident history, etc.

The potential in Big Data can take the current UBI models to an altogether different level. A convergence of multiple data dimensions can now be cohesively collected, analyzed, and modeled to offer truly dynamic, accurate and predictive risk management frameworks for insurers that maximize the benefit for the consumers. Through Big Data, insurers can include in addition to a consumer's driving patterns as seen through accelerator data, turn data, braking data, etc. and demographic & credit history; data dimensions such as current weather conditions, road traffic patterns and conditions, condition of the automobile, etc. These variables are entered into an algorithm for determining a customer's risk profile. A fully-utilized Big-Data-Driven-Insurance-Model would include real-time, dynamic weights for these variables, in addition to dynamic values for the variables themselves.

[Canada emerges as fertile ground for telematics]

As the UBI industry continues to develop, and Big Data becomes more prevalent, this model will disrupt the insurance industry and the way risk is calculated. Insurance firms that adopt a more comprehensive risk management framework incorporating key data variables will have a significant competitive advantage in driving "profitable growth" while maximizing "customer value."

In-car telematics systems could pair up with insurance firms to offer more comprehensive and effective UBI programs. This will be the big data world of machine data – the connected cars of tomorrow will continually generate this data, to be captured in real time and utilized by insurers for UBI coverage.

As the move toward dynamic pricing becomes more prominent, some firms will likely go farther than others. A lot of analysis and research will need to be done to determine how much of a person's risk profile can effectively be determined by static versus dynamic factors: Another entry point for big data and analytics. Firms must learn to strike this balance as they further develop their UBI programs.

Much of the literature around UBI comments on the consumer aversion toward providing information and additional data to insurance companies. It is true that this is a large jump for the current consumer mentality, however, these jumps have been made before. The growing popularity of applications like Venmo, Square, etc. is indicative of this shift toward information sharing. As acceptance of these technologies and information sharing grows, and the line that separates innovation from rants about 'Big Brother' continues to shift, this disruption has the potential to become an industry standard.

[Are Americans ready to trust telematics?]

About the author: Phani Nagarjuna is Founder & CEO of Nuevora, a premier Big Data Analytics & Apps firm. His operating experience of over 15 years includes global leadership positions across Product Management, Sales & Marketing, and Corporate Strategy and Turnaround.