Insurer trialing an intelligent machine learning-based solution that simplifies claims assessment
Prudential Singapore (Prudential) is leading a step change in the way insurance claims are made with its trial of an industry-first, machine learning-based solution that assesses claims in seconds.
It sits at the core of a new customer e-claims platform which Prudential is making available to selected insurance policyholders on a trial-basis.
The first phase of the trial, set to commence in late November 2017, will focus on automating the processing of PRUshield pre- and post- hospitalisation claims from eight major hospitals. These form the bulk of the 14,000 paper bills and receipts that Prudential’s claims assessors review each month.
The trial will simplify the process by allowing participants to upload scans or images of bills and invoices through the PRUaccess customer portal. This will significantly reduce the time that insurance claims assessors spend on handling paper-based submissions. The system’s intelligent decision-making capabilities aim to progressively shorten the claims assessment time from seven days down to mere seconds by the time the trial ends in the first half of 2018.
Ms. Theresa Nai, Chief Operating Officer at Prudential, said the move towards high precision, data-driven decision-making is part of the company’s wider digital roadmap to improve productivity and make insurance simpler for customers.
“We are continuously working on new technology solutions such as e-claims that will increase the convenience for our customers. Internally, e-claims cuts down the amount of manual work required and enables our people to focus on more meaningful customer engagement initiatives,” she said.
Intelligent e-claims solution powered by machine-learning
Once a participant uploads and submits a claim on the trial e-claims system, the inbuilt text-mining engine identifies and categorises payable and non-payable line items. Then, the intelligent machine-learning engine assesses the validity of the claim and recommends an o utcome (approve, partial approve or decline) and the payment amount.
The system has already been trained and back-tested using insurance claims data from the last two years and has reached a good level of accuracy. In the first phase of the trial, claims assessors will review the machine’s recommendations and provide feedback to the engine for continuous learning until it reaches an optimal level of confidence.
Prudential intends to fully launch the e-claims platform with straight-through processing capability in the second half of 2018.
No comments:
Post a Comment