Analytics, Artificial Intelligence (AI) and Machine Learning (ML) techniques are increasingly being used to help insurance providers make faster data driven decisions. Given the exponential level of data now available, AI/ML enables insurance providers to understand more clearly their customer’s needs and create stronger long-term value.
Making Insurance Pricing More Personalised
Starting with premium calculations, the insurance sector has access to thousands of data points to help set premiums. Machine learning algorithms quickly identify the most predictive attributes driving claims losses for example historical cancellation data and gaps in cover.
This helps insurers become more competitive, more effective in their pricing strategies and more targeted in writing risks that meet their underwriting appetite. In turn, customers receive more personalised quotes.
Creating a single customer view
Personalisation works best when you really know who you are dealing with. However, customer data held by insurance providers is often vastly under-utilised given the challenge of bringing data together from different parts of the business to create a single customer view. Mergers and acquisitions in the insurance market over the past few years have added to this challenge. Linking and matching technology using policy history data to find common threads helps overcome this problem to create one consolidated view of the customer to support all points of interaction – from quote to claim.
Making sense of masses of data
As the volume of data aggregated by insurance providers grows, cleansing and normalisation using ML techniques will become all the more important. For example, the data from connected cars and devices in the home – all that data needs to be gathered, normalised, standardised. This will help to ensure quality and consistency of the data so that consumers can shop for insurance based on their data if they choose, no matter the car make or model, smart home device or other IoT connected appliance or gadget.
Normalising Vehicle Data for insurance
Data normalisation is already helping insurance providers understand the presence of Advanced Driver Assistance Systems (ADAS) on a vehicle at the quotation stage. To solve the problem of the myriad of descriptors for ADAS, a classification system has been created using machine learning to scan millions of lines of car manufacturer vehicle data to logically sequence and classify vehicle safety features and component’s intended operation or purpose. Without the use of AI/ML, extraction and proper classification of this type of data would have been extremely difficult, time consuming and error prone.
Changing motor claims
AI and ML is also helping motor claims. In motor insurance within the US market for example, the claims processes have been improved through virtual claims handling and touchless claims handling. Here, image recognition technology is used to capture damage or invoices, run a system audit and if the claim meets the approved criteria, it is automatically paid without human involvement. This improves efficiency, cuts costs and smooths the customer journey.
Front of foot at FNOL
Through AI and ML techniques, telematics data can be used much more broadly than originally intended, allowing insurance providers to get on the front foot at first notification of loss (FNOL), helping to deliver a better consumer experience post-accident, whilst providing invaluable insights regarding the circumstances of the collision.
The conditions before, during and after the time of the accident can be communicated and claim severity analysed using data points like air bag deployment impact sensor activation and g-force metrics. Adding vehicle build data, insurance providers can understand the repair cost and potential impact to expensive ADAS features.
Improving the application process in home
In home insurance, conversion rates tend to be low due to a number of hard to answer questions along the customer journey. Prefill and data validation solutions are helping to make the application process easier but it has taken a huge amount of modelling, linking and AI and ML techniques to pull all the data together to return accurate and up-to-date information on the person and property.
Helping businesses understand local risks
In commercial property insurance, AI is already at play to provide valuable insights regarding a potential location for a new branch or business relocation. By sharing with customers local intelligence on footfall, crime rates, exposure to perils or other circumstances that increase risk, they may choose to take preventative measures if they move into that location. This decreases risk and loss costs for the insurance provider, whilst helping to improve customer experience and retention.
AI and ML in the democratisation of data
Finally, there is an increasing focus on educating consumers about how their data can be used and evaluated in a way they control and understand. A good example is the way driving behaviour data from aftermarket devices, or in the future, direct from the connected car gives a clearer picture of someone’s driving risk on the road, allowing consumers who have consented to share this data to benefit in potentially lower insurance costs and improved safety.
AI and ML automate and process the data consumers are happy to share – supporting greater choice, improved fairness and reduced friction with more personalised insurance protection.
Eleanor Brodie, Sr Manager, Data Science at LexisNexis Risk Solutions
