News from the Wire

One in 10 new merchants encounter rraud within first 90 days, Fraudio discovers

Tuesday, October 06, 2026 — 16:58:27 (UTC)

One in 10 New Merchants Encounters Fraud Within First 90 Days, Fraudio Data Discovers

New analysis finds median time to first fraud is just 33 days

More than four in five fraudulent transactions look ordinary when viewed in isolation

Fraudio uncovers fraud rates are 2.9 times higher in merchants’ first 90 days

Amsterdam, 06 Oct 2026 – One in 10 newly observed merchants experiences fraud within its first 90 days of trading, according to new analysis from AI-powered fraud detection company Fraudio, highlighting how quickly fraud can emerge before businesses have had time to establish a meaningful history of normal customer behaviour.

Fraudio analysed a global dataset consisting of a sample of more than 127.5 million transactions between January 2025 and April 2026. Among 3,923 merchants whose first recorded transaction took place during 2025, and which had not appeared in the data previously, 10.5% experienced at least one fraud-labelled transaction within their first 90 days.

For those merchants affected by fraud during their first 90 days, the median time from their first transaction to their first fraud was just 33 days. A quarter encountered fraud within nine days, while three quarters did so within 61 days.

Almost one in five of those merchants experienced their first fraud during their first week, while 47% experienced it within the first 30 days. The concentration was particularly pronounced at the beginning of the period, when adjusted for the different lengths of each time band, first frauds occurred at almost three times the daily rate during the first week compared with days 31 to 90.

The findings point to a fundamental challenge for fraud prevention that fraud can begin before a merchant has accumulated enough transaction history to establish reliable patterns of what legitimate activity looks like.

Fraudio's analysis also found that examining an individual payment in isolation provides relatively little indication of whether it will turn out to be fraudulent. Based only on the transaction's amount, currency and channel compared with that merchant's typical activity, 82% of fraudulent transactions appeared unremarkable. The equivalent figure for legitimate transactions was 84%, suggesting that these transaction-level attributes alone offer little ability to separate fraud from genuine payments.

By contrast, historical connections between transactions can be considerably more informative. Across the wider dataset, 30% of fraudulent transactions involved a card that had already been connected to an earlier fraud, compared with just 0.075% of legitimate transactions. Fraudio cautions that this is a retrospective measure because fraud labels can be confirmed by chargebacks after the original transaction, rather than a measure of what could necessarily have been known in real time.

João Moura, CEO and Co-Founder of Fraudio, commented,"Fraudsters don't wait for a business to build six months of transaction history before they begin attacking it. Our data shows that the opposite can happen as fraud can emerge within days, at exactly the point when a merchant has the least historical information available to understand what normal behaviour looks like.

"The other challenge is that fraudulent payments frequently don't look unusual when viewed on their own. The amount may be normal, the currency may be normal and the payment channel may be normal. What increasingly matters is the context around that transaction - what has happened before, how different entities are connected and whether apparently ordinary behaviour forms part of a wider pattern.

"Payment companies should not have to learn what fraud looks like by experiencing losses first. Fraud prevention needs to start with context from day one."

Fraudio's analysis also found that the fraud rate per transaction was 2.9 times higher during merchants' first 90 days than among payment programmes more than a year old, showing that early-stage merchants face a disproportionately higher fraud risk rather than simply accumulating more incidents over time.

The first 90 days in numbers: 10.5% of newly observed merchants experienced fraud within 90 days. 33 days was the median time to first fraud among those affected. 20% of early-hit merchants encountered their first fraud during their first week. 47% encountered it within their first 30 days. 82% of fraudulent transactions looked unremarkable when judged only by amount, currency and payment channel.

The merchant cohort comprised 3,923 businesses first observed during 2025. Fraudio's analysis uses fraud confirmed in its transaction data.

For more information about the data, please visit: go.fraudio.com/fraudio-data-led-insights

About Fraudio

Fraudio is a unified transaction risk platform for the payments industry, helping acquirers, issuers, processors, fintechs and merchants detect fraud, monitor merchant behaviour, and manage AML and compliance in one place.

Powered by a centralised, network-driven dataset spanning issuers, acquirers and the payment vehicles they process, Fraudio delivers real-time contextual analysis across transactions, merchants, cards and related entities. This allows clients to identify hidden patterns and emerging threats that would be impossible to detect within a single portfolio.

Its API-first, fully SaaS infrastructure fits into existing payment stacks and scales with ease. By combining AI-driven intelligence with flexible rules-based controls, Fraudio enables clients to reduce false positives, improve authorisation rates and make faster, more confident risk decisions.

For more information, visit fraudio.com

Notice to readers: These are archived articles. Contact information, links and other details may be out of date. We regret any inconvenience.

Source: Company press release.

Categories: Reports and research