Abstract: Marketing assets are automatically generated from asset components having asset features relevant to target users. Asset delivery event data regarding the delivery of marketing assets is initially collected to identify asset features of delivered marketing assets and user attributes of users receiving the marketing assets. The asset delivery event data is processed using machine-learning techniques to generate a model capable of selecting asset features given a set of user attributes. When a request for a new marketing asset is received for a particular user, user attributes of that user are identified and provided to the model to select a set of asset features. The asset features are used to select asset components, which are combined to form the new marketing asset.

Abstract: Marketing assets are automatically generated from asset components having asset features relevant to target users. Asset delivery event data regarding the delivery of marketing assets is initially collected to identify asset features of delivered marketing assets and user attributes of users receiving the marketing assets. The asset delivery event data is processed using machine-learning techniques to generate a model capable of selecting asset features given a set of user attributes. When a request for a new marketing asset is received for a particular user, user attributes of that user are identified and provided to the model to select a set of asset features. The asset features are used to select asset components, which are combined to form the new marketing asset.

Abstract: Methods and systems for analyzing usage and performance of digital design assets for asset selection. In particular, one or more embodiments maintain a digital design asset repository containing a plurality of digital design assets available for use in marketing campaigns. One or more embodiments assign asset identifiers to the digital design assets. One or more embodiments then track usage of and interactions with a first digital design asset in a plurality of marketing campaigns. One or more embodiments aggregate analytics data for the first digital design asset based on the tracked usage and interactions, and provide the aggregated analytics data with the first digital design asset in the digital design asset repository.

Abstract: Methods and apparatus for anomaly detection in network-site metrics using predictive modeling are described. A method comprises obtaining time-series data for a given time range, wherein the time-series data comprises values for a network-site analytics metric for each of a plurality of sequential time steps across the given time range. The method includes generating a predictive model for the network-site analytics metric based on at least a segment of the time-series data. The method includes using the predictive model to predict an expected value range for the network-site analytics metric for a next time step after the segment and, based on the expected value range, determining whether an actual value for the network-site analytics metric for the next time step is an anomalous value.

Abstract: Methods and apparatus for anomaly detection in network-site metrics using predictive modeling are described. A method comprises obtaining time-series data for a given time range, wherein the time-series data comprises values for a network-site analytics metric for each of a plurality of sequential time steps across the given time range. The method includes generating a predictive model for the network-site analytics metric based on at least a segment of the time-series data. The method includes using the predictive model to predict an expected value range for the network-site analytics metric for a next time step after the segment and, based on the expected value range, determining whether an actual value for the network-site analytics metric for the next time step is an anomalous value.

Abstract: Methods and apparatus for anomaly detection in network-site metrics using predictive modeling are described. A method comprises obtaining time-series data for a given time range, wherein the time-series data comprises values for a network-site analytics metric for each of a plurality of sequential time steps across the given time range. The method includes generating a predictive model for the network-site analytics metric based on at least a segment of the time-series data. The method includes using the predictive model to predict an expected value range for the network-site analytics metric for a next time step after the segment and, based on the expected value range, determining whether an actual value for the network-site analytics metric for the next time step is an anomalous value.

Abstract: Methods and apparatus for anomaly detection in network-site metrics using predictive modeling are described. A method comprises obtaining time-series data for a given time range, wherein the time-series data comprises values for a network-site analytics metric for each of a plurality of sequential time steps across the given time range. The method includes generating a predictive model for the network-site analytics metric based on at least a segment of the time-series data. The method includes using the predictive model to predict an expected value range for the network-site analytics metric for a next time step after the segment and, based on the expected value range, determining whether an actual value for the network-site analytics metric for the next time step is an anomalous value.