Abstract: In implementations of systems for predicting a terminal event, a computing device implements a termination system to receive input data defining a period of time and a maximum event threshold. This system uses a classification model to generate event scores for a plurality of entity devices. Each of the event scores indicates a probability of an event occurrence for a corresponding entity device within a period of time. The plurality of entity devices are segmented into a first segment and a second segment based on an event score threshold. Entity devices included in the first segment have event scores greater than the event score threshold and entity devices included in the second segment have event scores below the event score threshold. The termination system generates an indication of a probability that a number of event occurrences for the entity devices included in the second segment exceeds the maximum even threshold within the period of time.

Abstract: In implementations of systems for role classification, a computing device implements a role system to receive data describing a corpus of text that is associated with a user ID. Feature values of features are generated by a first machine learning model by processing the corpus of text, the features representing questions with respect to the corpus of text and the feature values representing answers to the questions included in the corpus of text. A classification of a role is generated by a second machine learning model by processing the feature values, the classification of the role indicating a relationship of the user ID with respect to a product or service. The role system outputs an indication of the classification of the role for display in a user interface of a display device.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for providing factors that explain the generated results of a deep neural network (DNN). In embodiments, multiple machine learning models and a DNN are trained on a training dataset. A preliminary set of trained machine learning models with similar results to the trained DNN are selected for further evaluation. The preliminary set of machine learning models may be evaluated using a distribution analysis to select a reduced set of machine learning models. Results produced by the reduced set of machine learning models are compared, point-by-point, to the results produced by the DNN. The best performing machine learning model with generated results that performs closest to the DNN generated results may be selected. One or more factors used by the selected machine learning model are determined.

Abstract: Techniques and systems are described for content interest from interaction information. Keywords are extracted from digital content, and relevance values are determined based on the keywords that captures both the statistical and semantic significance of topics in the digital content through use of a network representation. Interest values for an entity are determined based on the relevance values and an interaction dataset, which capture both the statistical and semantic significance of the topics with respect to the entity. The interest values may be utilized to control output of digital content to a client device.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for initiating electronic chats based on conversation workflows identified in response to detected user actions in connection with an embedded document container displaying a PDF file. In particular, in one or more embodiments, the disclosed systems detect user interactions with a PDF file displayed by a document container embedded in a webpage. The disclosed systems can determine whether the detected user interactions include or indicate a conversation workflow trigger associated with a conversation workflow. The disclosed systems can further generate electronic messages based on the conversation workflow and provide the generated electronic messages to the user in connection with the webpage where the document container is embedded.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for initiating electronic chats based on conversation workflows identified in response to detected user actions in connection with an embedded document container displaying a PDF file. In particular, in one or more embodiments, the disclosed systems detect user interactions with a PDF file displayed by a document container embedded in a webpage. The disclosed systems can determine whether the detected user interactions include or indicate a conversation workflow trigger associated with a conversation workflow. The disclosed systems can further generate electronic messages based on the conversation workflow and provide the generated electronic messages to the user in connection with the webpage where the document container is embedded.

Abstract: In implementations of systems for predicting a terminal event, a computing device implements a termination system to receive input data defining a period of time and a maximum event threshold. This system uses a classification model to generate event scores for a plurality of entity devices. Each of the event scores indicates a probability of an event occurrence for a corresponding entity device within a period of time. The plurality of entity devices are segmented into a first segment and a second segment based on an event score threshold. Entity devices included in the first segment have event scores greater than the event score threshold and entity devices included in the second segment have event scores below the event score threshold. The termination system generates an indication of a probability that a number of event occurrences for the entity devices included in the second segment exceeds the maximum even threshold within the period of time.

Abstract: In implementations of systems for role classification, a computing device implements a role system to receive data describing a corpus of text that is associated with a user ID. Feature values of features are generated by a first machine learning model by processing the corpus of text, the features representing questions with respect to the corpus of text and the feature values representing answers to the questions included in the corpus of text. A classification of a role is generated by a second machine learning model by processing the feature values, the classification of the role indicating a relationship of the user ID with respect to a product or service. The role system outputs an indication of the classification of the role for display in a user interface of a display device.

Abstract: Techniques and systems are described for content interest from interaction information. Keywords are extracted from digital content, and relevance values are determined based on the keywords that captures both the statistical and semantic significance of topics in the digital content through use of a network representation. Interest values for an entity are determined based on the relevance values and an interaction dataset, which capture both the statistical and semantic significance of the topics with respect to the entity. The interest values may be utilized to control output of digital content to a client device.

Abstract: An improved analytics system generates predicted event outcomes for events. The analytics system generates expected registration profiles based on event metadata that indicates predicted audience behavior for an event. This expected registration profile is used to analyze real-time audience behavior of an audience associated with the event. A predicted event outcome can be determined that indicates a time-based conversion propensity related to the audience.

Abstract: An improved marketing automation system can optimize governance of server resources by managing the execution of campaigns. The marketing automation system can develop intelligence around a given customer's inflow of incoming campaigns, the execution time of the campaigns, and general resource utilization over time. The marketing automation system can learn to predict an expected number and type of campaigns for a pre-defined window of time. This intelligence can be leveraged to ensure that one or more executors remain available to execute predicted high priority campaigns upon placement into an execution queue. Further, this intelligence can be applied such that predicted dormant executors can be used to execute low priority tasks. In this way, the marketing automation system minimizes queue time until execution for high priority campaigns while optimizing use of server resources.

Abstract: An improved marketing automation system can optimize governance of server resources by managing the execution of campaigns. The marketing automation system can develop intelligence around a given customer's inflow of incoming campaigns, the execution time of the campaigns, and general resource utilization over time. The marketing automation system can learn to predict an expected number and type of campaigns for a pre-defined window of time. This intelligence can be leveraged to ensure that one or more executors remain available to execute predicted high priority campaigns upon placement into an execution queue. Further, this intelligence can be applied such that predicted dormant executors can be used to execute low priority tasks. In this way, the marketing automation system minimizes queue time until execution for high priority campaigns while optimizing use of server resources.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for providing factors that explain the generated results of a deep neural network (DNN). In embodiments, multiple machine learning models and a DNN are trained on a training dataset. A preliminary set of trained machine learning models with similar results to the trained DNN are selected for further evaluation. The preliminary set of machine learning models may be evaluated using a distribution analysis to select a reduced set of machine learning models. Results produced by the reduced set of machine learning models are compared, point-by-point, to the results produced by the DNN. The best performing machine learning model with generated results that performs closest to the DNN generated results may be selected. One or more factors used by the selected machine learning model are determined.