Insurance: How to take better decisions using artificial intelligence

By implementing AI techniques with smaller use cases and simpler products, insurance companies can see how the results fare and scale AI adoption from there

Updated: Mar 20, 2019 12:43:38 PM UTC

Prashanth D is the Principal Consultant, Healthcare, Insurance and Life Sciences at Infosys.

Image: Shutterstock

Underwriting is a foundational process in all sectors of the insurance industry, yet the current process is laborious. Manual intervention can be very high, especially with life insurance--and human decision-making can lead to inconsistent results. Many insurance companies are also hampered by outdated technology and processes that keep them from leveraging the Internet of Things (IoT), including smartwatches and telematics devices that provide real-time data on activity levels and client driving performance.

A solution to these problems could be underwriting that is powered by artificial intelligence (AI). Without AI, some insurers take 20 to 30 days to decide on a life insurance applicant. With AI-powered underwriting, a decision could be reached weeks earlier. Since AI can derive insights from historical data, these decisions can also become more judicious. Currently, some insurance companies are using AI in small pockets, but there is yet to be widespread adoption of AI solutions across the underwriting landscape.

Under the AI spectrum, four techniques can be leveraged.

1. Machine learning
Insurance companies have vast amounts of historical data on applicants--medical history, family history, job data--as well as the risk assessment underwriters have assigned to applicants based on the available data and a static set of rules.

A machine-learning algorithm is capable of ingesting that historical data and creating a model that will mimic the decisions underwriters have made to that point. For less complex cases, allowing the model to assign the risk classification would move the industry closer to zero-touch underwriting, where decisions are made with zero manual intervention from the underwriter.

For more complex cases, the underwriter’s decision can be made quicker and with sounder judgment because the underlying model is there to support them. As the model matures and the organisation becomes more comfortable with AI, the percentage of applications underwritten with the zero-touch concept can increase.

2. Deep learning
With the advent of deep learning techniques, AI is becoming more sophisticated and better able to use reasoning and problem-solving skills in the way a human brain does. This will help transform the underwriting of various commercial risks currently being underwritten manually, using traditional methods, by expert underwriters. It will also enhance decision making and reduce costs (including underwriting losses).

Drones, equipped with infrared cameras, lasers, and sensors help gather data relating to weather, temperature and environmental conditions, including radiation. They are the game changers that are disrupting the way risk is being assessed in the commercial sector.

3. Natural language processing
Natural language processing has two applications within insurance. The first is that applicants can communicate with a bot to gather the information needed for an underwriter to make a risk assessment. The bot is able to understand the human it is communicating with due to the natural language processing technique. The other application is with text- based data mining--currently, a manual process for most insurance companies. With natural language processing, that information can be fed into a bot that instantly creates an electronic form. If machine learning is being utilised, that form can immediately be fed into the algorithm.

In commercial insurance, NLP can be used to better support the underwriters by being their virtual assistants. Apart from the usual data entry, NLP can help the underwriters to pull up relevant data on the risk they are writing using search-based analytics to speed up data access.

4. Behaviour data models
Behavioral data models can be used to analyse the real-time customer data from IoT devices for precise risk classification and product innovation. Using that data, insurance companies can launch new products that incentivise life insurance customers to lead healthier lives, or auto insurance customers to drive safer. When insurance companies leverage behavior data to combine a wellness product with traditional insurance, they can tap into a new market segment, a new revenue stream.

Overcoming barriers to adoption
Being able to issue policies faster will allow larger, more established companies to compete with technology-driven start-ups that are taking away their market share. However, most companies face barriers to adopting these solutions.

First barrier: Data capability
Historical insurance data is typically spread across disparate systems or applications, making it difficult for companies to pool together true and consistent data for a machine-learning algorithm to begin mining that data for insights.

Second barrier: Legacy technology
The existing technology used by most insurance companies is outdated enough that implementing AI techniques would require a significant financial investment, as well as a cultural shift within the organisation in terms of how technology is used in decision making.

Given these barriers, a ‘big bang’ approach is not recommended for companies looking to implement AI techniques within their underwriting department. Instead, companies should opt for a ‘start small and fail fast’ approach to achieve immediate wins and reduce the risks both financially and in terms of their time investment.

By implementing AI techniques with smaller use-cases and simpler products, insurance companies can see how the results fare and scale AI adoption from there.

The author is a Principal Consultant, Healthcare, Insurance and Life Sciences at Infosys.

Post Your Comment
Required, will not be published
All comments are moderated
Overlooked area for impact: Last-mile connectivity
Designer-less fashion: An industry waiting for AI disruption