18168602. METHODS AND SYSTEMS FOR PREDICTING FRAUDULENT TRANSACTIONS BASED ON ACQUIRER-LEVEL CHARACTERISTICS MODELING simplified abstract (MASTERCARD INTERNATIONAL INCORPORATED)

METHODS AND SYSTEMS FOR PREDICTING FRAUDULENT TRANSACTIONS BASED ON ACQUIRER-LEVEL CHARACTERISTICS MODELING

Organization Name

MASTERCARD INTERNATIONAL INCORPORATED

Inventor(s)

Shraddha Pandey of Pune (IN)

Anand Vir Singh Chauhan of Gwalior (IN)

Kushagra Agarwal of Jhansi (IN)

Tarun Somavarapu of Hyderabad (IN)

Shantanu Verma of Ghaziabad (IN)

Maneet Singh of New Delhi (IN)

METHODS AND SYSTEMS FOR PREDICTING FRAUDULENT TRANSACTIONS BASED ON ACQUIRER-LEVEL CHARACTERISTICS MODELING - A simplified explanation of the abstract

This abstract first appeared for US patent application 18168602 titled 'METHODS AND SYSTEMS FOR PREDICTING FRAUDULENT TRANSACTIONS BASED ON ACQUIRER-LEVEL CHARACTERISTICS MODELING

Simplified Explanation

The patent application describes a method and system for training a transaction monitoring model using a multi-component event-aware loss function. Here are some key points from the abstract:

• Access historical transaction data of payment transactions associated with an acquirer server.
• Determine acquirer features and transaction features based on the historical transaction data.
• Generate a latent representation for individual payment transactions using an embedding layer.
• Train a fraud classifier and an acquirer classifier based on the latent representation and the multi-component event-aware loss function.
• Compute the multi-component event-aware loss function based on the classifiers.
• Update network parameters based on the loss function.

Potential Applications

This technology could be applied in the financial industry for fraud detection and transaction monitoring systems.

Problems Solved

This technology helps in improving the accuracy and efficiency of fraud detection in payment transactions.

Benefits

The benefits of this technology include enhanced security, reduced fraud losses, and improved customer trust in payment systems.

Potential Commercial Applications

One potential commercial application of this technology could be in providing fraud detection services to financial institutions.

Possible Prior Art

One possible prior art for this technology could be existing fraud detection systems used in the financial industry.

Unanswered Questions

1. How does this technology compare to existing fraud detection systems in terms of accuracy and efficiency? 2. Are there any limitations or challenges in implementing this technology on a large scale in real-world payment systems?

Original Abstract Submitted

Embodiments provide methods and systems for training a transaction monitoring model based on a multi-component event-aware loss function. The method performed by a server system includes accessing historical transaction data of payment transactions associated with an acquirer server. Method includes determining acquirer features associated with the acquirer server and transaction features associated with an individual payment transaction based on the historical transaction data. Method includes generating, via an embedding layer, a latent representation corresponding to the individual payment transaction. Method includes training a fraud classifier and an acquirer classifier based on the latent representation and the multi-component event-aware loss function. Method includes computing the multi-component event-aware loss function based on execution of the fraud classifier and the acquirer classifier. Moreover, method includes updating network parameters of the fraud classifier, the acquirer classifier, and the embedding layer based on the multi-component event-aware loss function.