The DFX5 Artificial Intelligence and Machine Learning (AI/ML) practice group has developed a powerful fraud detection engine called LOGAN, which can detect fraud patterns, and abuse risks by using a combination of information found in typical credit card transactions.
LOGAN identifies five (5) types of online fraud in REAL-TIME:
- New Account Fraud Risk – Accurately distinguish between legitimate and high-risk customer account registrations so that you can selectively introduce additional steps or checks based on risk. For example, you can setup your customer account registration workflow to require additional email and phone verification steps only for account registrations that exhibit high risk characteristics.
- Guest Checkout Abuse – Spot potential fraudsters even among customers without a history of transactions. Guest checkout has no historical account usage or user behavior data which makes fraud detection much harder. With LOGAN, you can send as little as an email and IP address from a guest checkout order to assess its potential fraud risk so you can decide whether to accept it, review it, or collect more customer details.
- ‘Try Before you Buy’ Abuse – Identify accounts that are more likely to abuse “Try Before You Buy” programs such as fashion services that ship clothing and accessories for you to explore before sending payment.
- Online Payment Abuse – Reduce online payment fraud by flagging suspicious online payment transactions before processing payments and fulfilling orders.
- Account Takeover – Identify when an account of a current customer has been compromised by unapproved actors. Once identified then take actions to quickly eliminate the compromise, inform the client and take steps to avoid any potential financial risk.
Fraud is an ongoing problem that can cost businesses billions of dollars annually and damage customer trust. Some 15.4 million consumers were victims of identity theft or fraud last year, according to a new report from Javelin Strategy & Research. That’s up 16 percent and the highest figure recorded since the firm began tracking fraud instances in 2004.
LOGAN uses machine learning algorithms to detect the fraud scenarios. Traditional solutions use rule-based approaches to detect fraudulent activity, in where fraud patterns are defined as rules. However, implementing and maintaining
rules is a complex and expensive task. Thus, LOGAN provides an advantage in reducing costs of implementation and maintenance of fraud detection.
LOGAN, is a self-learning model that is constantly adapting to your specific fraud scenarios and will become more accurate as more events are processed. LOGAN uses a Linear Learner Algorithm, which brings state of the art computing power and combines it with complex mathematical theorems to detect fraud scenarios.
LOGAN identifies fraud cases without human intervention, thus delivering real-time automation. To maximize savings, the team built, trained and deployed the engine using Amazon Web Services (AWS). The integration with AWS allowed the team to reduce costs associated with the model. LOGAN can detect fraud instances using cloud native serverless applications and containers.
Contact the AI team at DFX5 today to find out how we can help you detect fraud instances by using LOGAN. Let us provide you with a cost-free and commitment-free analysis of how machine learning can help your business operate with more agility at a fraction of the cost.
Get started today!