Online payment fraud #
What is online payment fraud? #
Online payment fraud is when a fraudster uses false credentials to make purchases online. Fraudsters can obtain these credentials in several ways, which include account takeover (ATO), purchasing credit card details on the dark web, or gathering information via phishing.
Through online payment fraud, fraudsters can gain access to products at no cost for their personal use, or they can generate income by reselling these goods.
How Alphacomm prevents online payment fraud #
To prevent online payment fraud, we utilize the data sent to us via our API. Our anti-fraud solution evaluates whether the order appears fraudulent and provides a recommendation on whether you should accept it. Alphacomm solely offers guidance on accepting or declining, thereby clarifying how the order should be managed.
Alphacomm uses a unique combination of machine learning, rules and human supervision to provide advice:
Rules
Rules serve as an effective mechanism to enforce business logic and rapidly respond to changes, new patterns, and emerging fraud trends.
For instance, rules enable you to:
- Act fast to stop an attack
Fraud analysts can employ rules to halt a fraud attack promptly while it’s ongoing. - Proactively block new fraud trends
Fraud analysts can utilize rules to safeguard against emerging fraud trends before the machine learning model adjusts to such fraudulent behaviour. - Allow good customers
Rules can be used to allow and not just to prevent.
Alphacomm diligently performs around-the-clock surveillance on rule performance (24/7, 365 days a year), offering improvements whenever necessary.
Machine Learning
Alphacomm employs machine learning models, customized to fit your specific data, to deter online payment fraud. These models, with their adaptability and scalability, provide a robust defence, making them harder to bypass.
At Alphacomm, we are proactive in monitoring the performance of our machine learning models. Activities such as retraining of the models, threshold adjustment, and identification and integration of significant features are carried out consistently.
Analyst team
Our team of analysts works tirelessly, providing 24/7 transaction monitoring and swiftly responding to changes and potential attacks. This dedication ensures we consistently deliver the highest possible conversion rate all year round.
Data used #
Our online payment fraud models consider hundreds of customer features, for example:
- Merchant data:
The merchant provides Protectmaxx with transaction data, including details about what is purchased, when it’s purchased, and the method and location of purchase. - Payment information:
Paymaxx (or another PSP) provides information about payment status, method, and specific customer related data regarding the payment. - Third-party data:
We utilize third-party data to enrich profiles. This data may include email validation and Device ID. - Internal data:
Protectmaxx employs historical data to construct profiles that can aid in assessing current transactions. This is based on previous transactions, chargebacks, and so on. - Customer-specific data
We examine factors such as the email domain used by the customer and the age of the customer’s account. - Location information
Considerations include how the customer’s billing address differs from their delivery address. - Device information
We evaluate whether the device has been used for an order before and if it has been used by other customers.
