Abstract: A system for selecting one or more advertisement items to be presented to a user may include a computing device configured to obtain anchor item data including anchor item title data and anchor item metadata identifying characteristics of an anchor item. The computing device can also obtain advertisement item data including advertisement item title data and advertisement item metadata identifying characteristics of a plurality of advertisement items. The computing device can also determine a match score for each advertisement item of the plurality of advertisement items based on the anchor item data and the advertisement item data, wherein the match score identifies a relevance of the advertisement item to the anchor item. The computing device can then select one or more advertisement items based on the match score of each advertisement item.

Abstract: A system for selecting one or more advertisement items to be presented to a user may include a computing device configured to obtain anchor item data including anchor item title data and anchor item metadata identifying characteristics of an anchor item. The computing device can also obtain advertisement item data including advertisement item title data and advertisement item metadata identifying characteristics of a plurality of advertisement items. The computing device can also determine a match score for each advertisement item of the plurality of advertisement items based on the anchor item data and the advertisement item data, wherein the match score identifies a relevance of the advertisement item to the anchor item. The computing device can then select one or more advertisement items based on the match score of each advertisement item.

Abstract: A server computing system determines a plurality of statistics for a plurality of test documents, determines a number of false negatives for a corpus of documents based on one or more of the plurality of statistics for the plurality of test documents. The classification of a document of the corpus of documents is a false negative if classification of the document by a classification model is negative and classification of the document by a user is positive. The server computing system calculates an effectiveness of an information retrieval system on a corpus of documents based on the number of false negatives for the corpus of documents.

Abstract: A predictive coding system updates a plurality of training documents for an untrained classification model based on a plurality of additional documents. The plurality of additional documents are selected from a plurality of unlabeled documents based on a decision hyperplane associated with a first trained classification model. The predictive coding system provides the updated plurality of training documents to the untrained classification model to cause the untrained classification model to be retrained and to cause a second trained classification model to be generated.

Abstract: A server computing system determines a plurality of statistics for a plurality of validation documents. The server computing system determines a plurality of statistics for a plurality of test documents. The number of test documents in the plurality of test documents is determined based on the plurality of statistics for the plurality of validation documents and the effectiveness measure of interest. The server computing system calculates an effectiveness of an information retrieval system on a corpus of documents based on the plurality of statistics for the plurality of test documents.