Abstract: In an example embodiment, a skip logic using downsampling is applied to negative signals on a training data set fed to a machine-learning algorithm to train a machine-learned model. By downsampling the negatively labeled pieces of training data, the technical problem encountered in biasing the machine-learned model towards negative cases is overcome.

Abstract: Techniques for using online engagement footprints for video engagement prediction are provided. In one technique, events are received from multiple client devices, each event indicating a type of engagement of a video item from among multiple types of engagement. One or more machine learning techniques are used to train a prediction model that is based on the events and multiple features that includes the multiple types of engagement. In response to receiving a content request, multiple entity feature values are identified for a particular entity that is associated with the content request. Two or more of the entity feature values correspond to two or more of the types of engagement. A prediction is generated based on the entity feature values and the prediction model. The prediction is used to determine whether to select, from candidate content items, a particular content item that includes particular video.

Abstract: In an example embodiment, a debugging tool is provided that includes logging functionality to allow a machine learned model administrator to replay machine learned recommendation model executions in order to identify points of error, without the scaling difficulties that would be involved in logging all features used in every recommendation.

Abstract: In an example embodiment, cohort-based generalized linear mixed effect model (GLMIX) training is performed to identify patterns across cohorts of users, rather than slicing across all users blindly without accounting for common characteristics of users. Thus, rather than performing GLMIX training at just the finest granular level (e.g., user-level and job-level) or the highest level (global level), a “medium” level of granularity is used to train the GLMIX model at cohort-level.

Abstract: Methods, systems, and apparatus for accessing a set of feedback items, identifying a candidate feedback item from the set of feedback items using a lexical pattern, generating a gist phrase that summarizes the candidate feedback item, and causing display of a user interface on a client device, the user interface including the gist phrase.

Abstract: Methods, systems, and apparatus for predicting a status of a transaction are described. Feature data related to one or more transactions is collected and a subset of features is selected for use in predicting the status of the transaction. A model is trained using the collected feature data that corresponds to the selected features, and the model is applied to feature data of a selected transaction to generate a probability of the selected transaction attaining one or more defined statuses. Mitigating or preventive actions are performed based on the generated probability.

Abstract: Methods, systems, and apparatus for mining feedback are described. A set of one or more lexical patterns associated with one or more of a suggestion and a defect report are determined and the set of one or more lexical patterns are matched against a plurality of feedback items to generate a distance learning training set. A distance learning technique is applied to the distance learning training set to generate a distance learning model and the distance learning model is used to identify one or more candidate feedback items of the plurality of feedback items, each of which is one or more of a candidate suggestion and a candidate defect report.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system determines, based on data retrieved from a data store in an online system, features related to a user of the online system and an entity. Next, the system applies, to the features, a tree-based model that predicts outcomes between users and entities to generate a set of values representing interactions among the features. The system then inputs the set of values into a machine learning model to produce a score representing a likelihood of an outcome between the user and the entity. Finally, the system outputs a recommendation related to the user and the entity based on the score.

Abstract: The disclosed embodiments provide a system for identifying job seekers. During operation, the system determines, based on data retrieved from a data store in an online system, profile features produced from profile attributes in a profile of a first member in the online system and activity features produced from activity attributes that characterize activity of the first member with the online system. Next, the system applies a machine learning model to the profile features and the activity features to produce a score representing a likelihood that the first member is a job seeker. The system then applies a threshold to the score to generate a classification of the first member as the job seeker or as a non-job-seeker. Finally, the system updates, based on the classification, content outputted in a user interface of the online system by one or more electronic devices.

Abstract: Techniques for generating recommendations using a generalized linear mixed model with destination user personalization are disclosed herein. In some embodiments, a computer system generates corresponding scores for destination user candidates based on a generalized linear mixed model comprising a global model and a destination user model. The global model is a generalized linear model based on feature data of a source user and feature data of the destination user candidates, and the destination user model is a random effects model based on behavior data of the destination user candidates indicating whether the destination user candidates performed a destination user action in response to a source user action performed by reference source users similar to the source user. The computer system selects a subset of the destination user candidates for recommendation to the source user based on the scores of the subset of the destination user candidates.

Abstract: Techniques are provided for using machine learning techniques to learn embeddings for content items. In one technique, training data is used to learn embeddings for each attribute value of multiple attribute values of multiple content items, embeddings for each attribute value of multiple attribute values of multiple entities, and weights for a set of contextual features. In response to receiving a content request, a content item that is associated with one or more targeting criteria that are satisfied based on the content request is identified. A first set of embeddings for the content item are identified, a requesting entity that initiated the content request is identified along with a second set of embeddings for the requesting entity, and a set of feature values for the set of contextual features is identified. The content item is selected based on the sets of embeddings, the set of feature values, and the weights.

Abstract: Techniques for using online engagement footprints for video engagement prediction are provided. In one technique, events are received from multiple client devices, each event indicating a type of engagement of a video item from among multiple types of engagement. One or more machine learning techniques are used to train a prediction model that is based on the events and multiple features that includes the multiple types of engagement. In response to receiving a content request, multiple entity feature values are identified for a particular entity that is associated with the content request. Two or more of the entity feature values correspond to two or more of the types of engagement. A prediction is generated based on the entity feature values and the prediction model. The prediction is used to determine whether to select, from candidate content items, a particular content item that includes particular video.

Abstract: Methods, systems, and apparatus for predicting a status of a transaction are described. Feature data related to one or more transactions is collected and a subset of features is selected for use in predicting the status of the transaction. A model is trained using the collected feature data that corresponds to the selected features, and the model is applied to feature data of a selected transaction to generate a probability of the selected transaction attaining one or more defined statuses. Mitigating or preventive actions are performed based on the generated probability.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of segments from a job posting, wherein each segment in the set of segments includes a portion of text in the job posting. Next, the system applies a model to the set of segments to produce a set of labels for the set of segments, wherein each label in the set of labels represents a type of information in the job posting. The system then stores the segments with the labels for use in matching the job posting to a candidate.

Abstract: Methods, systems, and apparatus for mining feedback are described. A set of one or more lexical patterns associated with one or more of a suggestion and a defect report are determined and the set of one or more lexical patterns are matched against a plurality of feedback items to generate a distance learning training set. A distance learning technique is applied to the distance learning training set to generate a distance learning model and the distance learning model is used to identify one or more candidate feedback items of the plurality of feedback items, each of which is one or more of a candidate suggestion and a candidate defect report.

Abstract: Methods, systems, and apparatus for predicting a status of a transaction are described. Feature data related to one or more transactions is collected and a subset of features is selected for use in predicting the status of the transaction. A model is trained using the collected feature data that corresponds to the selected features, and the model is applied to feature data of a selected transaction to generate a probability of the selected transaction attaining one or more defined statuses. Mitigating or preventive actions are performed based on the generated probability.

Abstract: Methods, systems, and apparatus for mining feedback are described. A set of one or more lexical patterns associated with one or more of a suggestion and a defect report are determined and the set of one or more lexical patterns are matched against a plurality of feedback items to generate a distance learning training set. A distance learning technique is applied to the distance learning training set to generate a distance learning model and the distance learning model is used to identify one or more candidate feedback items of the plurality of feedback items, each of which is one or more of a candidate suggestion and a candidate defect report.

Abstract: Methods, systems, and apparatus for predicting a status of a transaction are described. Feature data related to one or more transactions is collected and a subset of features is selected for use in predicting the status of the transaction. A model is trained using the collected feature data that corresponds to the selected features, and the model is applied to feature data of a selected transaction to generate a probability of the selected transaction attaining one or more defined statuses. Mitigating or preventive actions are performed based on the generated probability.

Abstract: Methods, systems, and apparatus for mining feedback are described. A set of one or more lexical patterns associated with one or more of a suggestion and a defect report are determined and the set of one or more lexical patterns are matched against a plurality of feedback items to generate a distance learning training set. A distance learning technique is applied to the distance learning training set to generate a distance learning model and the distance learning model is used to identify one or more candidate feedback items of the plurality of feedback items, each of which is one or more of a candidate suggestion and a candidate defect report.