Detection of malicious activity within a network

A network-based authentication system comprising:

• one or more processing units, each processing unit comprising one or more processors;
• and
• one or more memory devices respectively coupled to and readable by the one or more processing units, the memory devices storing therein one or more sets of instructions which, when executed by the processing units, causes one or more computer devices to:
• receive a network transaction;
• identify a first attribute of the network transaction;
• select a first learning statistical model and a second learning statistical model from a plurality of models for handling the network transaction, wherein:
• the first learning statistical model and the second learning statistical model are selected based on the first attribute of the network transaction;
• and
• each of the first learning statistical model and the second learning statistical model create a likelihood that the network transaction is authentic;
• calculate, using the first learning statistical model, a first score;
• calculate, using the second learning statistical model, a second score;
• compare the first score to a first threshold and the second score to a second threshold;
• authenticate the network transaction based on comparing the first score to the first threshold and the second score to the second threshold;
• and
• in response to authentication of the network transaction, complete, by the network-based authentication system, the network transaction.

A non-transitory computer-readable medium having stored thereon a series of instructions which, when executed by one or more processors of a network-based authentication system, cause the one or more processors to detect malicious activity within a network by:

• receiving a network transaction;
• identifying a first attribute of the network transaction;
• selecting a first learning statistical model and a second learning statistical model from a plurality of models for handling the network transaction, wherein:
• the first learning statistical model and the second learning statistical model are selected based on the first attribute of the network transaction;
• and
• each of the first learning statistical model and the second learning statistical model create a likelihood that the network transaction is authentic;
• calculating, using the first learning statistical model, a first score;
• calculating, using the second learning statistical model, a second score;
• comparing the first score to a first threshold and the second score to a second threshold;
• authenticating the network transaction based on comparing the first score to the first threshold and the second score to the second threshold;
• and
• in response to authenticating the network transaction, completing, by the network-based authentication system, the network transaction.