US 2025/0029107 A1 · MULTIMODAL FRAUD DETECTION AND PREVENTION FOR ELECTRONIC PAYMENT PLATFORMS

Abstract

In one example, the disclosed multimodal fraud prevention techniques are employed by an intermediary settlement platform. The intermediary settlement platform generally monitors transaction data associated with various payment rails and provides new store and forward functions, which include receiving new customer transactions before they reach core services associated with a Financial Institution (FI); executing new transactions as predicted transactions; extracting behavior metrics from the predicted transactions; quantifying predicted fraud prior to settlement (e.g., before transferring funds) using comprehensive customer identity behavior models; and performing fraud interventions based on the same. In this example, the intermediary settlement platform creates the customer identity behavior models and transforms the customer's transaction data into comprehensive behavior metrics according to the dimensions of the respective model; quantifies the customer behaviors for new transactions; and determines the degree of predicted behavior conformance between the new transaction and non-fraudulent customer behavior metrics.

Claims20

Dependent claims

A multimodal fraud prevention system, comprising:

one or more network interfaces configured to communicate with one or more electronic payment rails over a network;
a processor coupled to the one or more network interfaces;
and
a memory configured to store instructions, the instructions are executable by the processor and are operable to:
create a customer profile having one or more customer identity behavior models, the one or more customer identity behavior models represent expected customer behavior associated with at least one registered device and with non-fraudulent transactions;
receive transaction data associated with a new transaction;
convert at least a portion of the transaction data into new respective behavior metrics for corresponding dimensions of at least one customer identity behavior model;
quantify a degree of predicted behavior conformance between the new respective behavior metrics and the expected customer behavior for the corresponding dimensions of the at least one customer identity behavior model;
determine a predicted fraud score for the new transaction based on the degree of predicted behavior conformance;
and
perform one or more fraud interventions when the predicted fraud score exceeds a predetermined fraud threshold.

8 more elements

A tangible, non-transitory, computer-readable media having instructions encoded thereon, the instructions are executable by a processor and are operable to:

create a customer profile having one or more customer identity behavior models, the one or more customer identity behavior models represent expected customer behavior associated with at least one registered device and with non-fraudulent transactions;
receive transaction data associated with a payment rail in a network, the transaction data corresponds to a new transaction;
convert at least a portion of the transaction data into new respective behavior metrics for corresponding dimensions of at least one customer identity behavior model;
quantify a degree of predicted behavior conformance between the new respective behavior metrics and the expected customer behavior for the corresponding dimensions of the at least one customer identity behavior model;
determine a predicted fraud score for the new transaction based on the degree of predicted behavior conformance;
and
perform one or more fraud interventions when the predicted fraud score exceeds a predetermined fraud threshold.

4 more elements

A method for preventing fraud, comprising:

creating a customer profile having one or more customer identity behavior models, the one or more customer identity behavior models represent expected customer behavior associated with at least one registered device and with non-fraudulent transactions;
monitoring one or more electronic payment rails over a network for transaction data;
determining at least a portion of the transaction data is associated with a new transaction;
converting at least the portion of the transaction data into new respective behavior metrics for corresponding dimensions of at least one customer identity behavior model;
quantifying a degree of predicted behavior conformance between the new respective behavior metrics and the expected customer behavior for the corresponding dimensions of the at least one customer identity behavior model;
determining a predicted fraud score for the new transaction based on the degree of predicted behavior conformance;
performing one or more fraud interventions when the predicted fraud score exceeds a predetermined fraud threshold;
and
communicating with one or more core services at a financial institution to facilitate settlement of the new transaction when the predicted fraud score does not exceed the predetermined fraud threshold.

6 more elements

Dependencies are inferred from the claim text.

Multimodal fraud detection and prevention for electronic payment platforms

Life of this patent

Multimodal fraud detection and prevention for electronic payment platforms

Life of this patent

Abstract

Claims20