Abstract: An ordered combination of machine-learning models may be used to identify users who are likely to abandon use of an application, predict the reasons why those users are likely to abandon, and identify intervening actions that the application can perform to reduce the probability that the users will abandon the application. For example, a first machine-learning model determines a retention-prediction value indicating a probability that the user will complete a target action in the application before a session terminates. If the retention-prediction value satisfies a threshold condition, a second machine-learning model determines a reason why the session is likely to terminate before the user completes the target action. A third machine-learning model determines an intervention action for the application to perform to increase the probability that the user will complete the target action before the session terminates.

Abstract: Certain aspects of the present disclosure provide techniques for determining query intent and complexity based on text input. One example method generally includes receiving, from a user device, a text query and preprocessing the text query to generate a query vector. The method further includes providing the query vector to an intent model configured to output a user intent of the text query and providing the query vector to a complexity model configured to output a complexity of the text query. The method further includes receiving the user intent of the text query from the intent model and receiving the complexity of the text query from the complexity model. The method further includes determining, based on the user intent and the complexity of the query, a routing target for the text query and routing the text query to the routing target.

Abstract: Systems described herein apply an ordered combination machine-learning models to identify users who are likely to abandon use of an application, predict the reasons why those users are likely to abandon, and identify intervening actions that the application can perform to reduce the probability that the users will abandon the application. A first machine-learning model determines a retention-prediction value indicating a probability that the user will complete a target action in the application before a session terminates. If the retention-prediction value satisfies a threshold condition, a second machine-learning model determines a reason why the session is likely to terminate before the user completes the target action. A third machine-learning model determines an intervention action for the application to perform to increase the probability that the user will complete the target action before the session terminates.

Abstract: Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions to the user.

Abstract: Systems described herein apply an ordered combination machine-learning models to identify users who are likely to abandon use of an application, predict the reasons why those users are likely to abandon, and identify intervening actions that the application can perform to reduce the probability that the users will abandon the application. A first machine-learning model determines a retention-prediction value indicating a probability that the user will complete a target action in the application before a session terminates. If the retention-prediction value satisfies a threshold condition, a second machine-learning model determines a reason why the session is likely to terminate before the user completes the target action. A third machine-learning model determines an intervention action for the application to perform to increase the probability that the user will complete the target action before the session terminates.

Abstract: An ordered combination of machine-learning models may be used to identify users who are likely to abandon use of an application, predict the reasons why those users are likely to abandon, and identify intervening actions that the application can perform to reduce the probability that the users will abandon the application. For example, a first machine-learning model determines a retention-prediction value indicating a probability that the user will complete a target action in the application before a session terminates. If the retention-prediction value satisfies a threshold condition, a second machine-learning model determines a reason why the session is likely to terminate before the user completes the target action. A third machine-learning model determines an intervention action for the application to perform to increase the probability that the user will complete the target action before the session terminates.

Abstract: Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions to the user.

Abstract: Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions to the user.

Abstract: A method and system provides personalized user experiences to users of a tax return preparation system, at least partially based on likelihoods of occurrence of life events for the users in a tax year, according to one embodiment. The method and system applies the user data to one or more predictive models to determine the likelihood that one or more available life events occurred in a user's life in a tax year, according to one embodiment. The method and system display life event icons that represent the one or more available life events, and the life event icons are ranked, sorted, and/or emphasized, based on the likelihood that the one or more available life events occurred in a user's life, to increase a user's confidence in the tax return preparations system's capability to address the user's life changes while preparing the user's tax return, according to one embodiment.

Abstract: Method and apparatus for providing a personalized self-support service to a user of an online application coupled with an online community forum. Embodiments include obtaining a plurality of questions from the online community forum and obtaining historical user data. Embodiments further include identifying one or more part-of-speech words in the plurality of questions and generating a high-dimensional vector for each question of the plurality of questions based on a frequency of the one or more part-of-speech words. Embodiments further include identifying one or more user features of the plurality of users based on the historical user data and establishing, based on the historical user data, one or more statistical correlations between user features and part-of-speech words. Embodiments further include training a predictive model based on the one or more statistical correlations. Embodiments further include using the predictive model to predict to provide one or more relevant questions to the user.

Abstract: A method and system facilitates the development of data science transformations in one programming language and the deployment of the data science transformations in another programming language, according to one embodiment. The method and system preserves relationships, functions, configurations, and characteristics between combinations of data transformations, according to one embodiment. The preservation of the relationships, functions, configurations, and characteristics is enabled by developing and providing a set of low-level (e.g., atomic) transformations that enable users to build their own models, libraries, and configurations into macro-transformations (e.g., conglomerate transformations), according to one embodiment.

Abstract: A method and system facilitates the development of data science transformations in one programming language and the deployment of the data science transformations in another programming language, according to one embodiment. The method and system preserves relationships, functions, configurations, and characteristics between combinations of data transformations, according to one embodiment. The preservation of the relationships, functions, configurations, and characteristics is enabled by developing and providing a set of low-level (e.g., atomic) transformations that enable users to build their own models, libraries, and configurations into macro-transformations (e.g., conglomerate transformations), according to one embodiment.

Abstract: A system and method for monitoring the storage estate of an organization using an interactive website that is configured to produce and display a novel set of key performance indicators (KPIs) related to the storage estate, including KPIs related to data collected from at least one of storage area network data and network attached storage data. In one embodiment, the novel set of KPIs includes one or more of protection efficiency, application efficiency, and snapshot overhead, where protection efficiency is calculated as a ratio of logical addressable data storage volume to total physical volume of data storage for storage area network data of the organization, application efficiency is calculated as a fraction of disk storage allocated to end user devices that is actually used by the end user devices for storage area network data, and snapshot overhead is calculated as a ratio of a volume of storage allocated for replicated copies of data to allocated storage for network attached storage data.

Abstract: A system and method for monitoring the storage estate of an organization using an interactive website that is configured to produce and display a novel set of key performance indicators (KPIs) related to the storage estate, including KPIs related to data collected from at least one of storage area network data and network attached storage data. In one embodiment, the novel set of KPIs includes one or more of protection efficiency, application efficiency, and snapshot overhead, where protection efficiency is calculated as a ratio of logical addressable data storage volume to total physical volume of data storage for storage area network data of the organization, application efficiency is calculated as a fraction of disk storage allocated to end user devices that is actually used by the end user devices for storage area network data, and snapshot overhead is calculated as a ratio of a volume of storage allocated for replicated copies of data to allocated storage for network attached storage data.