Systems and methods for automatic identification of anomalous data

A method for automatic identification of anomalous data, comprising:

• receiving, by a computing system comprising one or more processors, a plurality of items of data;
• for each item of data of the plurality of items of data:
• extracting, by the computing system using a trained language model, a plurality of keywords, and
• generating, by the computing system, a vector based on the extracted plurality of keywords;
• grouping, by the computing system, the vectors into one or more clusters in an n-dimensional space by determining a centroid for each of the one or more clusters, and:
• (a) assigning vectors to a cluster based on a distance between the vector and the centroid being less than a first threshold,
• (b) determining whether a percentage of vectors not assigned to any cluster is less than a second threshold, and
• (c) repeating (a)-(b) while adjusting the first threshold until the percentage of vectors not assigned to any cluster is equal to or greater than the second threshold;
• identifying, by the computing system, at least one item of data corresponding to a vector external to every cluster of the one or more clusters;
• and
• providing, by the computing system, the identified at least one item of data as anomalous data.

A system for automatic identification of anomalous data, comprising:

• a computing system comprising one or more processors, the one or more processors configured to:
• receive a plurality of items of data;
• for each item of data of the plurality of items of data:
• extract, using a trained language model, a plurality of keywords, and
• generate, by the computing system, a vector based on the extracted plurality of keywords;
• group the vectors into one or more clusters in an n-dimensional space by determining a centroid for each of the one or more clusters, assigning vectors to a cluster based on a distance between the vector and the centroid being less than a threshold, and adjusting the threshold until a predetermined percentage of vectors are external to every cluster of the one or more clusters;
• identify at least one item of data corresponding to a vector external to every cluster of the one or more clusters;
• and
• provide the identified at least one item of data as anomalous data.