ANZ Wealth has revealed it is collaborating with researchers at the University of Technology Sydney (UTS) to explore how machine learning models can improve the insurance underwriting process.
A partnership with the university’s Advanced Analytics Institute (AAi) is investigating how client behaviour modelling (which is concerned with analysing the responses personal statements and understanding the relationship between certain questions and outcomes), text mining and natural language processing, as well as social and predictive analytics, can “add value in the insurance sector”.
The collaboration has been ongoing since 2016 but revealed for the first time this week.
“An intelligent underwriting model will harness machine learning to provide opportunity for insurers to develop more efficient and reliable assessment processes,” said UTS associate professor Guandong Xu.
As part of the collaboration, the use of AI to improve the customer experience of the application process is also being investigated.
“A data-driven model provides the opportunity to create a more personalised, efficient service with improved quality assurance for our customers when they apply for insurance,” said Peter Tilocca, chief underwriter at ANZ Wealth.
“AI can also provide our advisers with a differentiated service that supports them in building trusted relationships with their clients.”
The AAi has worked with a number of financial institutions including Credit Suisse, Westpac, AMP and HCF.
In 2016 the institute worked with wealth management group Colonial First State to build advanced analytics models to observe complex relationship patterns between investors, employers and financial planners and build predictive models to help improve customer service.
“We aim to be the leading research group in applying data analytics and AI in FinTech across various wealth sectors such as insurance, superannuation and investment portfolios,” Xu said.
Given the wealth of data available to insurers, the sector is considered ripe for disruption from machine learning techniques.
Despite this, the industry has been slow to move, with a 2016 analysis finding less than 2 per cent of insurance companies were investing in AI. However, in another survey, 98 per cent of insurance executives agreed AI will play a disruptive role in the industry, 85 per cent believed it will be critical to the future of their business and, as a result, 96 per cent said they intend to invest in cognitive capabilities in the future.
A 2017 Deloitte report said those insurers that were using AI were focused on optimising existing services and processes.
“These efforts are already yielding tangible benefits. However, insurers are lagging behind in leveraging AI to discover new insights in operations and customer interactions,” the report states.
InsurTech start-ups like Clover, Lemonade, GetSafe and Fabric have been quick to adopt machine learning techniques in a bid to disrupt the big players.
Last year, Japanese firm Fukoku Mutual Life Insurance made headlines after laying off 34 employees and replacing them with a system based on IBM’s Watson.
The company said it expected to increase productivity by 30 per cent and see a return on investment within two years.
A spokesperson for ANZ indicated to Computerworld that the bank was seeking to use AI to support rather than replace staff.
"Underwriters will be able to use AI for standard processes and allow them to focus more on complex technical cases to derive the best decisions for customers," the spokesperson said.