Methods and systems for determining provenance and identity of digital advertising requests solicited by publishers and intermediaries representing publishers

A computer implemented method for determining provenance and identity of a digital advertising request for an advertisement solicited by at least one of a publisher and an intermediary representing the publisher, wherein the method comprises:

• receiving, with a transceiver of a first computing device, a first message having a plurality of first message metrics associated with a candidate entity for identification;
• processing, with a processor of the first computing device, the first message to identify a first portion of a candidate entity identity based on the plurality of first message metrics;
• generating, with the processor, a first response to the first message based on which of at least one respective currently unknown message metric of the first message exhibits an instability;
• receiving, with the transceiver, from the candidate entity a first reply to the first response;
• processing, with the processor, the first reply to identify a second portion of the candidate entity identity;
• and,
• producing, with the processor, an output related to confidence of the candidate entity identity based on the first portion and second of the candidate entity identity.

A computer implemented method for determining provenance and identity of a digital advertising request for an advertisement solicited by at least one of a candidate entity and an intermediary representing the candidate entity, wherein the method comprises identifying a portion of a candidate entity identity comprising:

• identifying, with a processor of a first computing device, a plurality of message metrics associated with a message from a candidate entity;
• converting, with the processor, each of the plurality of message metrics to at least one message embedding, wherein the at least one message embedding represents at least a coordinate in a dimension of a plurality of dimensions;
• combining, with the processor, the at least one message embedding to a coordinate tensor;
• and,
• identifying, with the processor, on the coordinate tensor at least one of (i) at least one candidate entity cluster associated with the least one message embedding and (ii) no candidate entity cluster with the least one message embedding.