SAS Hackathon team, Data Hack Freaks, created an artificial intelligence (AI) and machine learning (ML) based dynamic pricing approach that allows insurance providers to adjust pricing based on the changing nature of the risk behavior of their customers.
This solution has three major components: The loss ratio score, telematics score and environment and social governance (ESG) score.
Meeting the models
Let’s talk about the first model, the loss ratio score. This model looks at a company’s coverage type, number of vehicles in the fleet, their types, value, age, capacity and location. The purpose of the model is to predict potential losses and suggest the right risk segment. It helps optimize risk-based pricing. Based on the forecast, insurers can offer high-risk customers a higher premium and low-risk customers a lower premium. They do this by introducing telematics and ESG to traditional pricing. Not only does this benefit the insured, but insurers, too.
The next model is the telematics score. Car manufacturers have been installing telematics devices in vehicles. It can reflect driving behavior by using these devices to look at the speed, acceleration, sudden braking and turning of an individual vehicle. The model gives each driver a score when all this information is recorded. These scores are recorded over time, and the insurance company can determine if the drivers are at higher or lower risk and adjust the premium based on the data.
The third model is the ESG score. The purpose of this model is to capture the effect fleet operators have on the environment. The ESG model calibrates the environmental score by using the vehicle discharge rate for gases like carbon dioxide, carbon monoxide and nitrogen oxide. Depending on how harmful a truck may be to the environment can also affect the premium that is offered.
A win-win scenario with dynamic pricing
These three models offer a more flexible approach to dynamic pricing and allow insurers and the insured to receive benefits. The solution also offers reusable components such as a weather software interface, ESG data interface, AI/ML frameworks, dynamic pricing and risk analyses dashboards. Insurers that deal with fleet operators receive business benefits too. It reduces accident, maintenance and environmental costs and prevents insurers from fraudulent claims. Further, it helps increase efficiency throughout the business and spotlight what is working and what is not.
As a next step, the team plans to develop and scale this solution to apply it to a real-client environment. The team hopes that they will be able to flip the industry trend, allowing for low losses and increasing profit.
