8th October, 2020
Fraud prevention specialists are delving into what sort of novel buying patterns are emerging as they look to foil fraudsters’ plans for fraudulent transactions.
A major concern, as always, is to ensure a fraudster’s attempt shouldn’t go unnoticed, whereas a genuine customer doesn’t end up being denied to pay for a transaction.
Think of evolving purchasing hours, device usage…there are too many variables to consider.
How to tackle the issue then?
Machine learning’s role in fraud detection can’t be undermined but it shouldn’t be forgotten that it takes time to recalibrate. Relying only on transactional data may not work at this juncture.
A human fraud analyst can take charge and control the situation, ensuring a genuine shopper’s experience isn’t hampered. Reviewing transactions manually is equally important. It is imperative to make the most of an automated machine learning system with a rules-based approach.
Cybersource aptly puts it – it is time to let merchants “play by their own rules”. If machine learning needs time to recalibrate to new trends, they can adjust settings themselves in their tools to minimize any negative impact. Analysts can work on business rules to eradicate false positives.
Join experts and explore new trends in payments and fraud at Ai’s Airline & Travel Payment Summit
#ATPS Virtual Conference 2020: 20 - 22 Oct 2020