Abstract: A method and system provide estimated tax refund data to a user of a tax return preparation system throughout personalized tax return preparation interview. The method and system receive current user tax related data associated with the user, retrieve tax rules data, and gather historical tax related data associated with historical users of the tax return preparation system. The method and system further generate probabilistic inference data including inferences about tax related characteristics of the user based on the historical tax related data and the tax rules data. The method and system provide estimated tax refund data to the user based on the probabilistic inference data.

Abstract: Systems and methods for generating recommended offers are disclosed. An example method may be performed by one or more processors of a recommendation system and include correlating attributes of users with attributes of offers based on historical data associated with the users and offers, training a machine learning model to predict a user's interest in an offer based on the correlating, obtaining current user data, obtaining current offer data, providing the current user data and the current offer data to the trained machine learning model, generating, using the trained machine learning model, a predicted level of interest that the current user has in each respective current offer of the number of current offers, identifying, among the number of current offers, at least one current offer having a predicted level of interest for the current user greater than a value, and generating one or more recommended offers for the current user.

Abstract: User data from users/consumers is transformed into machine learning training data including historical offer attribute model training data, historical offer performance model training data, and user attribute model training data associated with two or more users/consumers, and, in some cases, millions, tens of millions, or hundreds of millions or more, users/consumers. The machine learning training data is then used to train one or more offer/attribute matching models in an offline training environment. A given current user's data and current offer data are then provided as input data to the offer/attribute matching models in an online runtime/execution environment to identify current offers predicted to have a threshold level of user interest. Recommendation data representing these offers is then provided to the user and the current user's actions with respect to the recommended offers is monitored and used as online training data.

Abstract: Big data analysis methods and machine learning based models are used to provide offer recommendations to consumers that are probabilistically determined to be relevant to a given consumer. Machine learning based matching of user attributes and offer attributes is first performed to identify potentially relevant offers for a given consumer. A de-duplication process is then used to identify and eliminate any offers represented in the offer data that the consumer has already seen, has historically shown no interest in, has already accepted, that are directed to product or service types the user/consumer already owns, for which the user does not qualify, or that are otherwise deemed to be irrelevant to the consumer.

Abstract: A method and system provide estimated tax refund data to a user of a tax return preparation system throughout personalized tax return preparation interview. The method and system receive current user tax related data associated with the user, retrieve tax rules data, and gather historical tax related data associated with historical users of the tax return preparation system. The method and system further generate probabilistic inference data including inferences about tax related characteristics of the user based on the historical tax related data and the tax rules data. The method and system provide estimated tax refund data to the user based on the probabilistic inference data.

Abstract: A method and system provide estimated tax refund data to a user of a tax return preparation system throughout personalized tax return preparation interview. The method and system receive current user tax related data associated with the user, retrieve tax rules data, and gather historical tax related data associated with historical users of the tax return preparation system. The method and system further generate probabilistic inference data including inferences about tax related characteristics of the user based on the historical tax related data and the tax rules data. The method and system provide estimated tax refund data to the user based on the probabilistic inference data.

Abstract: Computing systems, computer-implemented methods, articles of manufacture for making personalized assessments regarding whether a taxpayer should be presented with a standardized flow of interview screens, questions or topics, or with an itemized deduction flow of interview screens, questions or topics. This assessment is made utilizing a generated user interface and analytic data elements that generate outputs that reflect the taxpayer's data, e.g., in the form of ranges of numerical data that are based on the taxpayer's data. User interface elements representing response options in the form of range data may be selected by the user without entering specific electronic tax return data for the purpose of making standardized v. itemized determinations and to determine which questions or topics can be bypassed.

Abstract: Big data analysis methods and machine learning based models are used to provide offer recommendations to consumers that are probabilistically determined to be relevant to a given consumer. Machine learning based matching of user attributes and offer attributes is first performed to identify potentially relevant offers for a given consumer. A de-duplication process is then used to identify and eliminate any offers represented in the offer data that the consumer has already seen, has historically shown no interest in, has already accepted, that are directed to product or service types the user/consumer already owns, for which the user does not qualify, or that are otherwise deemed to be irrelevant to the consumer.

Abstract: Big data analysis methods and machine learning based models are used to provide offer recommendations to consumers that are probabilistically determined to be relevant to a given consumer. Machine learning based matching of user attributes and offer attributes is first performed to identify potentially relevant offers for a given consumer. A de-duplication process is then used to identify and eliminate any offers represented in the offer data that the consumer has already seen, has historically shown no interest in, has already accepted, that are directed to product or service types the user/consumer already owns, for which the user does not qualify, or that are otherwise deemed to be irrelevant to the consumer.

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: A system and method for use with a data management service provides aggregated statistics derived from a large amount of user data extracted from one or more transaction management systems. The aggregated statistics are based on client queries from client systems. The queries request statistical information about a queried user grouping. An input interpreter module uses machine learning to modify the queried user grouping into a plurality of improved user groupings. A statistics calculator module performs a set of calculations on the user data based on the improved user groupings, and returns the results to an output preparer module. The output preparer module uses machine learning to determine which aggregated statistic to return to the client system.

Abstract: A method and system identifies users who benefit from filing itemized deductions over standardized deductions to reduce an average time consumed for users preparing tax returns with a tax return preparation system, according to one embodiment. The method and system receives user data that is associated with a user, and applies the user data to a predictive model to cause the predictive model to determine a likelihood that the user will decrease his/her taxable income by filing an itemized deduction, according to one embodiment. The method and system deemphasizes and/or postpones the presentation of tax return questions that are related to the itemized deduction, if the likelihood that the user will decrease his/her taxable income by filing the itemized deduction is below a threshold, to reduce a quantity of time consumed by the user to prepare his/her tax return with a tax return preparation system, according to one embodiment.

Abstract: A method and system improve retention of a user of a tax return preparation system by personalizing a tax return preparation interview with questions that are at least partially based on user data processed by one or more predictive models, according to one embodiment. The method and system include receiving user data that is associated with a user, and applying the user data to one or more predictive models to cause the one or more predictive models to generate predictive output data, according to one embodiment. The predictive output data are scores for a subset of questions, and scores represent a relevance to the user of each of the subset of questions, according to one embodiment. The method and system include presenting selected ones of the subset of questions to the user, at least partially based on the scores, to personalize a tax return preparation interview for the user.

Abstract: A method and system applies analytics models to a tax return preparation system to determine a likelihood of qualification for an earned income tax credit by a user, according to one embodiment. The method and system receive user data and applying the user data to a predictive model to cause the predictive model to determine, at least partially based on the user data, a likelihood of qualification for an earned income tax credit for the user, according to one embodiment. The method and system display, for the user, an estimated tax return benefit to the user, at least partially based on the likelihood of qualification for the earned income tax credit exceeding a predetermined threshold, to reduce delays in presenting estimated earned income tax credit benefits to the user during a tax return preparation session in a tax return preparation system, according to one embodiment.

Abstract: Biometric data is collected to obtain more detailed, connected, and reliable feedback data from users of an interactive software system that has a more empirical and objective basis. The biometric data is then used to create emotional pattern predictive model data representing emotional pattern predictive models associated with users of the interactive software system. The individual emotional pattern predictive models associated with multiple users of the interactive software system are then analyzed and processed to generate emotional pattern profile data for categories of users. These biometric data based predictive models are then used for targeted product diagnosis, targeted interventions, targeted marketing/upsell attempts, and grouping and analysis of feedback and user categories and feedback sources.

Abstract: A method and system identifies users who benefit from filing itemized deductions over standardized deductions to reduce an average time consumed for users preparing tax returns with a tax return preparation system, according to one embodiment. The method and system receives user data that is associated with a user, and applies the user data to a predictive model to cause the predictive model to determine a likelihood that the user will decrease his/her taxable income by filing an itemized deduction, according to one embodiment. The method and system deemphasizes and/or postpones the presentation of tax return questions that are related to the itemized deduction, if the likelihood that the user will decrease his/her taxable income by filing the itemized deduction is below a threshold, to reduce a quantity of time consumed by the user to prepare his/her tax return with a tax return preparation system, according to one embodiment.