Methods and systems for assessing excessive accessory listings in search results

A computer-implemented method, comprising:

• parsing, by at least one processor, a data field of a document and generating at least one token from the data field;
• calculating, by the at least one processor, a score for the at least one token, the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications;
• calculating, by the at least one processor, a score for the document based on the at least one token score, the document score representing a probability of the document being in one of the two binary classifications;
• inputting the document score and document attribute values into a decision tree;
• and
• generating an output using the decision tree, the output representing a refined score for the document based on the document score and at least one of the document attribute values.

A machine-readable storage medium storing a set of instructions that, when executed by at least one processor, causes the at least one processor to perform operations comprising:

• parsing a data field of a document and generating at least one token from the data field;
• calculating a score for the at least one token, the at least one token score representing a likelihood that the at least one token belongs to one of two binary classifications;
• calculating a score for the document based on the at least one token score, the document score representing a probability of the document being in one of the two binary classifications;
• inputting the document score and document attribute values into a decision tree;
• and
• generating an output using the decision tree, the output representing a refined score for the document based on the document score and at least one of the document attribute values.

A computer-implemented method, comprising:

• parsing, by at least one processor, a search query received from a user to identify keywords;
• identifying at least one dominant category using the keywords, the at least one dominant category including documents containing the keywords;
• determining an intent of the search query using the keywords, the intent related to a class of documents to be returned from two binary classifications of documents;
• grouping the documents in the at least one dominant category into the two binary classifications, the grouping based on a score calculated for each document in the at least one dominant category, the score representing a probability that the document belongs in one of the two binary classifications;
• providing a subset of the documents to the user, the subset of the documents being the documents grouped in one of the two binary classifications, the one of the binary classifications identified based on the intent of the search query;
• and
• ordering the subset of the documents according to at least one of the document scores and a document attribute.

A system, comprising:

• a processor-implemented query interpreter module configured to:
• parse a search query received from a user to identify keywords;
• identify at least one dominant category using the keywords, the at least one dominant category including documents containing the keywords;
• and
• determine an intent of the search query using the keywords, the intent related to a class of documents to be returned from two binary classifications of documents;
• and
• a processor-implemented ranking module configured to:
• group the documents in the at least one dominant category into the two binary classifications, the grouping based on a score calculated for each document in the at least one dominant category, the score representing a probability that the document belongs in one of the two binary classifications;
• provide a subset of the documents to the user, the subset of the documents being the documents grouped in one of the two binary classifications, the one of the binary classifications identified based on the intent of the search query;
• and
• order the subset of the documents according to at least one of the document scores and a document attribute.