Amsterdam-based FinTech startup Dimebox has launched a proprietary fraud predictor service based on machine learning.
The company has released the service to detect evolving fraud patterns, allowing fraudulent payments to be blocked. It trains itself on batches of transactions that are known to be legitimate or fraudulent, from specific merchant databases, creating a deep understanding of the kind of fraud that is targeting individual merchants.
Within the Dimebox platform, transaction rulesets can then be employed to automatically stop a transaction before it is completed, if the predicted likelihood of fraud is above a defined threshold.
It uses self-learning algorithms to calculate a fraud score for every transaction, allowing the user to decide whether or not the score is high enough to warrant blocking, in the context of other criteria.
Dimebox was founded in 2014 by industry experts from Adyen, Paysafe and Ingenico. It offers its customers a white-label full-service payment gateway for all their payments, providing them with tools to increase automation and reduce costs.
Because the Dimebox full-stack white-label acquiring platform offers end-to-end processing, fraud data is collected directly by the gateway, via chargebacks and fraud reports—Visa’s “TC40” report and Mastercard’s “SAFE” report— through direct access to card issuers.
By adding the fraud predictor feature to their platform, Dimebox expands their fraud offerings for merchants, PSPs and acquirers by increasing authorisation rates and minimizing chargebacks, while eliminating the need for large fraud analysis teams.
Last year, the company raised €5m in a Series A round from the BillPro Group, a leading global payment processing organisation.
Copyright © 2018 RegTech Analyst
Copyright © 2018 RegTech Analyst
