Abstract: At an artificial intelligence-based service, an indication of a similarity group of items of a data stream is obtained. A subset of the stream items is to be included in an ordered collection and presented via an interface which allows one or more types of interactions. Using a first data set which includes interaction records of items in the similarity group, one or more machine learning models are trained to predict a relevance metric associated with a particular type of interaction. A predicted value of the relevance metric is obtained from a trained version of a model and stored.

Abstract: The arrangement and selection of digital content to present to a user can be based at least in part upon the relevance of content, e.g., the probabilities of the user selecting to view more information and/or otherwise engaging with instances of the content. Features of items associated with content presented to a user can be determined, as well as the user's response to items with those features. This data is used to determine the probability of the user viewing and/or otherwise engaging an item having specific values for at least some of those features. The probabilities are combined with abandonment scores associated with a feed position of an interface to ensure that content displayed is optimized for engagement. The items can be ranked based on this engagement determination, in order to select which item content to display and the appropriate arrangement of that content.

Abstract: The effect of position bias on content performance can be determined in part using artificial intelligence and computer learning. Performance data can include the frequency with which an action, such as a purchase, occurs in response to an instance of content being displayed. The content can be associated with a node at a lowest level of an offering hierarchy, and performance data from the various levels can be rolled up to higher level nodes to obtain sufficient data to for accurate position bias determinations. A bias model can be trained using the data from the various levels, where the training determines weightings for the bias determinations of each level. Once the position bias for an offer is determined, a normalized performance value can be obtained that does not include the effects of the bias. The normalized values can be used to select and place content based on actual performance.

Abstract: An example of a method includes determining features of a first type for a web page of a plurality of web pages. The method also includes electronically determining a plurality of rules for an attribute of the first web page, wherein the plurality of rules are determined based on features of the first type. The method also includes electronically identifying a first rule, from the plurality of rules, which satisfies a first predefined criterion. The first predefined criteria include at least one of a first threshold for a precision parameter, a second threshold for a support parameter, a third threshold for a distance parameter and a fourth threshold for a recall parameter. The method further includes storing the first rule to enable extraction of value of the attribute from a second web page.

Abstract: A method includes generating, electronically, one or more matching patterns for one or more pairs of attribute values. Each pair includes two attribute values. The two attribute values include a first attribute value from a first record and a second attribute value from a second record. The first attribute value and the second attribute value satisfy a first criterion. Further, the method includes identifying, electronically, matching segment between the first attribute value and the second attribute value of a first pair. The method also includes repeating identifying for each pair. Moreover, the method includes computing a similarity score for the first pair using one of the first pair and the matching segment based on the one or more matching patterns and matching segments of the one or more pairs satisfying a second criterion. The method also includes repeating computing for each pair.

Abstract: A set of clusters associated with a plurality of web pages is received. A first data set and a second data set are generated by applying a first rule and the second rule, respectively, to web pages of a first cluster of the set of clusters. The second rule is substituted for the first rule responsive to having an acceptable extraction accuracy when applied to the first cluster. The extraction accuracy of the second rule is determined by comparing attributes of the second data set to attributes of the first data set.

Abstract: An example of a method includes determining features of a first type for a web page of a plurality of web pages. The method also includes electronically determining a plurality of rules for an attribute of the first web page, wherein the plurality of rules are determined based on features of the first type. The method also includes electronically identifying a first rule, from the plurality of rules, which satisfies a first predefined criterion. The first predefined criteria include at least one of a first threshold for a precision parameter, a second threshold for a support parameter, a third threshold for a distance parameter and a fourth threshold for a recall parameter. The method further includes storing the first rule to enable extraction of value of the attribute from a second web page.

Abstract: A method includes generating, a plurality of sets of pairs of records from a set of records, for each attribute-position pair in the set of records. Each attribute-position pair being indicative of a position of an attribute in a record. Further, the method includes forming, electronically, a plurality of groups, each group comprising two attribute-position pairs having different attributes. Further, the method also includes determining, electronically for each group, number of pairs of records that are common in the two attribute-position pairs of that group. Furthermore, the method includes extracting results based on a first group of the plurality of groups if the number of pairs of records that are common in the two attribute-position pairs of the first group is greater than a second threshold, is highest among the plurality of groups, and no group having three or more attribute-position pairs with different attributes is possible.

Abstract: A method includes generating, electronically, one or more matching patterns for one or more pairs of attribute values. Each pair includes two attribute values. The two attribute values include a first attribute value from a first record and a second attribute value from a second record. The first attribute value and the second attribute value satisfy a first criterion. Further, the method includes identifying, electronically, matching segment between the first attribute value and the second attribute value of a first pair. The method also includes repeating identifying for each pair. Moreover, the method includes computing a similarity score for the first pair using one of the first pair and the matching segment based on the one or more matching patterns and matching segments of the one or more pairs satisfying a second criterion. The method also includes repeating computing for each pair.