Monzo uses TensorFlow machine learning to cut card fraud losses to under 0.01% of top-up volume
Criminals were purchasing stolen card details online and topping up Monzo prepaid cards to convert stolen card numbers into physical spending power; Monzo would then absorb chargeback losses from the genuine cardholders. Prepaid card schemes were especially attractive targets because the conversion from stolen details to a usable card was straightforward.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Top-up request received
A user initiates a top-up of their Monzo card using another debit card, making Monzo the acquiring merchant.
Tools used
Tensorflow
Outcome
Monthly fraud losses fell to under 0.01% of total top-up volume (from a high of 0.84%), the false positive ratio improved from 6 genuine users banned per 3 fraudsters to 1, and the overall fraud rate is now an order of magnitude below the financial services industry average.
What failed first
In the early months of the fraud system (May–June 2016), the false positive rate was extremely high — Monzo was banning six genuine users for every three fraudsters caught — and financial losses from fraud reached a high of 0.84% of top-up volume.
Results
Time saved0.84%
Volumeorder of magnitude lower than the financial services industry average
Cost replacedless than 0.01%
Running sinceover the last six months (relative to February 2017 publication)