Abstract: This disclosure involves performing event analytics on-the-fly based on user input to an analysis interface. An event analytics system correlates a plurality of event datasets to include a common visitor identifier. The system causes display, via the analysis interface, of information about the plurality of event datasets. The system receives, via the analysis interface, user selection of one or more event datasets, of the plurality of event datasets. Based on the selected one or more event datasets, the system generates a combined event dataset. The event analytics system receives, via the analysis interface, user input specifying information requested about the combined event dataset. The system obtains the requested information about the combined event dataset. The system causes display, via the analysis interface, of a visualization of the obtained information, wherein the visualization is based on event data from the combined event dataset in chronological order.

Abstract: Creating an association of a user identifier linked to a mobile device with the presentation of content. A computing device may create an association between the presentation of content on a presentation device and a user identifier linked to a mobile device in response to the presentation of content. The computing device may detect a presentation event which indicates a connection between a user identifier linked to the mobile device and the presentation of content. The computing device may then send a presentation event message to a network server. Subsequently, a predefined event may be detected via the mobile device, and in response, a predefined event message, including the user identifier linked to the mobile device and the predefined event, may be sent to the network server.

Abstract: The present disclosure covers systems and methods for collecting and analyzing analytics data for a plurality of online user interactions and aggregating the analytics data to determine sentiment scores and generate a presentation of a path of interactions. For example, the systems and methods analyze the analytics data to identify attributes of the online user interactions and determine, based on the identified attributes, a sentiment score for each of the plurality of online user interactions. In addition, the systems and methods aggregate the plurality of online user online user interactions to identify an interaction path commonly experienced by the users of the interactions. Further, the systems and methods generate and provide an interactive presentation including a visualization of the interaction path and associated ranges of sentiment scores associated with types of online user interactions that make up the interaction path.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating webpage design templates based on product information, audience information, and user experience information. For example, the disclosed systems can utilize an internet-based product catalog engine to determine actual product information such as product descriptions and reviews to include within a webpage design template during the design process. The disclosed systems can further generate personalization rules to modify the appearance of a product webpage to accommodate the preferences of different audiences. In addition, the disclosed systems can generate recommendations to modify various design elements based on product information, audience information, and user experience information. Further, the disclosed systems can publish a webpage design template as a product storefront webpage accessible to end users.

Abstract: The present disclosure is directed toward systems and methods for identifying contributing audience segments associated with a metric anomaly. One or more embodiments described herein identify contributing factors based on statistical analysis and machine learning. Additionally, one or more embodiments identify audience segments associated with each contributing factor. In one or more embodiments, the systems and methods provide an interactive display that enables a user to select a particular anomaly for further analysis. The interactive display also provides additional interfaces through which the user can view informational displays that illustrate the factors and segments that caused the particular anomaly and how those factors correlate with each other.

Abstract: The present disclosure is directed toward systems and methods for identifying contributing factors associated with a metric anomaly. One or more embodiments described herein identify contributing factors based on statistical analysis and machine learning. Additionally, one or more embodiments identify sub-factors associated with each contributing factor. In one or more embodiments, the systems and methods provide an interactive display that enables a user to select a particular anomaly for further analysis. The interactive display also provides additional interfaces through which the user can view informational displays that illustrate the factors that caused the particular anomaly and how those factors correlate with each other.

Abstract: The present disclosure is directed toward systems and methods for identifying contributing audience segments associated with a metric anomaly. One or more embodiments described herein identify contributing factors based on statistical analysis and machine learning. Additionally, one or more embodiments identify audience segments associated with each contributing factor. In one or more embodiments, the systems and methods provide an interactive display that enables a user to select a particular anomaly for further analysis. The interactive display also provides additional interfaces through which the user can view informational displays that illustrate the factors and segments that caused the particular anomaly and how those factors correlate with each other.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating webpage design templates based on product information, audience information, and user experience information. For example, the disclosed systems can utilize an internet-based product catalog engine to determine actual product information such as product descriptions and reviews to include within a webpage design template during the design process. The disclosed systems can further generate personalization rules to modify the appearance of a product webpage to accommodate the preferences of different audiences. In addition, the disclosed systems can generate recommendations to modify various design elements based on product information, audience information, and user experience information. Further, the disclosed systems can publish a webpage design template as a product storefront webpage accessible to end users.

Abstract: An unsupported event module may install one or more event handlers in an application, wherein the one or more event handlers are configured to catch user interface events not otherwise handled by the application. During execution of the application, one or more unsupported event handlers may record user interface events not otherwise handled by the application. The method further includes storing or transmitting one or more records of the user interface events recorded by the one or more unsupported event handlers. Other embodiments may include receiving, from a plurality of remote computing devices, records of user interface events. The recorded user interface events from a plurality of computers implementing instances of an application may be aggregated to generate a report indicting the number of user interface events not otherwise handled for the application.

Abstract: The present disclosure is directed toward systems and methods for identifying contributing factors associated with a metric anomaly. One or more embodiments described herein identify contributing factors based on statistical analysis and machine learning. Additionally, one or more embodiments identify sub-factors associated with each contributing factor. In one or more embodiments, the systems and methods provide an interactive display that enables a user to select a particular anomaly for further analysis. The interactive display also provides additional interfaces through which the user can view informational displays that illustrate the factors that caused the particular anomaly and how those factors correlate with each other.

Abstract: This disclosure relates to dynamic determination of data-transmission characteristics based on historical data accesses. For example, some embodiments include accessing a content stream having (i) a first content item and a second content item to be provided to one or more user devices associated with a user and (ii) a trigger condition for providing the second content item. In addition, some embodiments include detecting that the first content item has been consumed at the one or more user devices through a first communication channel and, further, determining that the trigger condition has been met. A machine-learning model inputs action data to determine a second communication channel from among two or more available communication channels. In some cases, the second content item is triggered to be delivered via the second communication channel, responsive to the first content item being consumed and the trigger condition being met.

Abstract: View location metric generation and engagement attribution within an AR or VR environment are described. In one example, a system of a digital medium environment is configured to generate metric data describing viewed locations within an augmented or virtual reality environment. The system includes a log data collection module implemented at least partially in hardware of a computing device to collect log data from a plurality of user devices. The log data describes locations associated with an augmented or virtual reality environment and a viewing direction at corresponding locations. The system also includes a metric generation module implemented at least partially in hardware of the computing device to generate metric data describing viewed locations within the augmented or virtual reality environment by the plurality of user devices and an output module implemented at least partially in hardware of the computing device to output the generated metric data.

Abstract: Various embodiments describe techniques for dynamically customizing structured interactive content for a particular user within a session of an interactive computing environment. Machine-learning techniques are used to establish a behavioral class of each individual user based on user interactions with a diagnostic set of interactive content items during the session. The identified behavioral class is used to customize interactive content presented later during the session using various machine-learning techniques. In some embodiments, the user progress during the session is determined based on user interactions with the customized interactive content, and a content customization is performed if the user progress is below a threshold value.

Abstract: In some embodiments, a real-time and interactive preview of alerts is provided in a user interface. A computer system parses a set of rules that specifies an alert definition. Each rule identifies a set of observations and an alert trigger criterion based on user input in the user interface. For a rule, the computer system accesses historical data corresponding to the set of observations identified by the rule and determines, based on an analysis of the historical data, time points that trigger alerts over a time period according to the rule. The analysis is based on the alert trigger criterion identified by the rule. The computer system aggregates, based on the alert definition, the time points determined for the rule with time points determined for another rule from the set of rules. Further, the computer system generates an alert preview over the time period for presentation at the user interface.

Abstract: In some embodiments, a contact stream is generated or modified based on configuration data received from a machine-learning model. Multiple contact items are selected for a contact stream, to be delivered to a user device via electronic communication channels. In addition, a success metric is identified indicating an engagement with the contact stream or an action performed following the engagement. A machine-learning model is applied to the contact items, where the machine-learning model is trained to identify relationships among actions in an online environment and configuration parameters that control delivery of contact streams. The machine-learning model provides an output indicating configuration data or a success probability for the contact stream. The configuration data includes configuration parameter values computed by the machine-learning model for achieving the identified success metric.

Abstract: This disclosure relates to dynamic determination of data-transmission characteristics based on historical data accesses. For example, some embodiments include accessing a content stream having (i) a first content item and a second content item to be provided to one or more user devices associated with a user and (ii) a trigger condition for providing the second content item. In addition, some embodiments include detecting that the first content item has been consumed at the one or more user devices through a first communication channel and, further, determining that the trigger condition has been met. A machine-learning model inputs action data to determine a second communication channel from among two or more available communication channels. In some cases, the second content item is triggered to be delivered via the second communication channel, responsive to the first content item being consumed and the trigger condition being met.

Abstract: An improved analytics system generates product interest profiles for customers that are related to post-purchase interactions with a product by a customer. The analytics system receives product metadata from a catalog that is related to the product purchased by the customer. The analytics system can further receive social content of the customer from a social channel. The social content is analyzed for post-purchase interactions with the product purchased by the customer. A product interest profile is generated for the customer related to the product based at least in part on the post-purchase interaction.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating webpage design templates based on product information, audience information, and user experience information. For example, the disclosed systems can utilize an internet-based product catalog engine to determine actual product information such as product descriptions and reviews to include within a webpage design template during the design process. The disclosed systems can further generate personalization rules to modify the appearance of a product webpage to accommodate the preferences of different audiences. In addition, the disclosed systems can generate recommendations to modify various design elements based on product information, audience information, and user experience information. Further, the disclosed systems can publish a webpage design template as a product storefront webpage accessible to end users.

Abstract: Techniques are disclosed for identifying a video using a video signature generated using image features derived from a portion of the video. In some examples, a method may include determining image features derived from a portion of a video, determining a video frame sequence of the video, and generating the video signature of the video based on the image features and the video frame sequence. The method may further include deriving a curve for the video based on the image features and the video frame sequence, and comparing the derived curve with one or more curves corresponding to respective one or more reference videos.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that provide an attribution user interface that integrates attribution models as native components within the interface to configure analytics visualizations. By integrating attribution models and corresponding functions as native components of a user interface, the disclosed methods, non-transitory computer readable media, and systems can implement attribution models as parameters of attribution distributions or of any attribution visualizations, where the attribution models function as event categories. For instance, the disclosed methods, non-transitory computer readable media, and systems can provide analytics tools to generate visualizations of different attribution distributions of events across dimension values (or other visualizations) based on different attribution models.