Photo Source: Good Free Photos
The recent explosion of inexpensive monitoring systems, uninterrupted data streams, and artificial intelligence to make sense of the torrent of information has made widespread surveillance and analytics affordable, not just for government agencies but for corporations as well. One sector of the business world—auto insurance—has fully embraced monitoring as a new way to adjust insurance premiums in an active and near real-time manner.
Plenty of auto insurance commercials, often humorously, depict various drivers in situations being tempted to drive recklessly. For example, one of State Farm’s Drive Safe & Save commercials depicts a woman, Kim, in different situations under pressure from her passengers to speed up, such as her daughter having to use the restroom, but she snaps, “Don’t mess with my discount!” The commercial refers to a new type of insurance premium setting called UBI or usage-based insurance.
UBI collects information in real-time such as rapid acceleration, hard breaking, hard turning, time of day, and location to determine the safety of a driver. Such data gets processed over time, and a driving profile gets created and used to adjust the driver’s insurance premium. In other words, safer driving habits bring discounts. Traditionally, insurance premiums depended on such factors as past driving performance, age, sex, vehicle type, neighborhood of residence and other factors like academic performance. For example, two drivers that look the same on paper but from different areas would pay different premiums if one lived in a neighborhood with a light accident history and the other in one with more frequent accidents.
Researchers from the University of British Columbia and Perdue University published research based on analysis of data collected by an insurance company from drivers using a UBI system to see if the monitoring did improve driver safety over time. In their paper titled “Sensor Data and Behavioral Tracking: Does Usage-Based Auto Insurance Benefit Drivers?,” Miremad Soleymanian, Charles B. Weinberg, and Ting Zhu found that after twenty-six weeks of monitoring that overall drivers improved their safe driving habits including a decrease of 21% of hard breaking, yet the daily driving distance did not decrease. (Marketing Science, 2019) Interestingly, they also found that young drivers and female drivers improved the safety of their driving more then males and older people. The authors concluded that UBI monitoring provides a net benefit to the public with safer driving habits, to the insurance companies with more accurate insurance adjustments, and the individual with monetary benefits for safe driving.
Insurance companies have introduced a new way of determining driver safety that uses real-time driver monitoring or user-based insurance to identify safe drivers and to incentivize safe driving through insurance discounts. Driver monitoring based on the research presented by Soleymanian and others appears to improve safe driving habits for some segments of the population. However, one study does not address other issues with driver monitoring and feedback. For example, research detailed in a paper titled “Does Real-time Feedback Make You Try Less Hard? A Study of Automotive Telematics” based on driver monitoring and feedback showed that drivers who reviewed their detailed driver feedback performed 13% worse than drivers who did not review their feedback, and they also showed a decrease in the time between accidents. (insead.edu) The authors speculate that some drivers will put in less effort when they get a good score, and on the other hand, drivers with a more perfectionist personality will get discouraged when getting negative feedback from real-time monitoring, leading to poorer driving performance. User-based insurance employs real-time data to adjust insurance premiums with the promise of lower costs to good drivers, but it may not be the case that people will respond to driver monitoring and feedback. Before committing to a UBI system, consider if it will genuinely benefit you, as it actually may not.
Dr. Smith’s career in scientific and information research spans the areas of bioinformatics, artificial intelligence, toxicology, and chemistry. He has published a number of peer-reviewed scientific papers. He has worked over the past seventeen years developing advanced analytics, machine learning, and knowledge management tools to enable research and support high level decision making. Tim completed his Ph.D. in Toxicology at Cornell University and a Bachelor of Science in chemistry from the University of Washington.
You can buy his book on Amazon in paperback here and in kindle format here.