Method and system for detecting fraudulent transactions

A system for detecting fraudulent transactions, the system comprising:

• a server configured to:
• generate, based on historical transaction data of a plurality of historical transactions, a graph that includes a plurality of nodes and a plurality edges between the plurality of nodes, wherein each historical transaction of the plurality of historical transactions is executed between a consumer of a set of consumers and a merchant of a set of merchants, and wherein the plurality of nodes include a set of merchant nodes corresponding to the set of merchants and a set of consumer nodes corresponding to the set of consumers;
• determine a set of static features based on the historical transaction data and a plurality of dynamic features based on the generated graph;
• and
• train a neural network based on the set of static features and the plurality of dynamic features, for detection of transaction fraud, wherein the trained neural network is used to detect a first transaction as one of a fraudulent transaction and a legitimate transaction based on first transaction data of the first transaction.

A method for detecting fraudulent transactions, the method comprising:

• receiving, by a server, first transaction data for a first transaction;
• providing, by the server, the first transaction data as input to a neural network that is trained based on a set of static features and a plurality of dynamic features, wherein the set of static features is determined from historical transaction data of a plurality of historical transactions and the plurality of dynamic features are determined from a graph that includes a plurality of nodes and a plurality weighted edges between the plurality of nodes, and wherein the plurality of nodes include a set of merchant nodes corresponding to a set of merchants in the plurality of historical transactions and a set of consumer nodes corresponding to a set of consumers in the plurality of historical transactions;
• and
• detecting, by the server, the first transaction as one of a fraudulent transaction and a legitimate transaction based on an output of the trained neural network for the first transaction data.