Embodiments of this application disclose a recommendation method. The method in embodiments of this application may be applied to a scenario such as a movie recommendation scenario or a game recommendation scenario in which an item is recommended to a user. The method includes: obtaining preliminary recommendation ranking indicating a plurality of to-be-recommended items; and obtaining ranking of a plurality of historical items related to historical behavior of a user, and updating the preliminary recommendation ranking based on a second feature obtained based on the ranking of the plurality of historical items. Because the second feature reflects a preference degree of the user for a category to which the plurality of historical items belong, a third sequence determined based on the second feature can provide personalized and diversified item recommendation for the user.

An estimation device includes an input unit that generates supervised data including causal variables, process types, and outcome variable for each of multiple processes, and a training unit that uses the supervised data to generate a learning model by learning the outcome variables from the causal variables and the process types for each of the processes.

An automated integrated dataset marketplace method is disclosed. The method includes capturing and processing user data from transactions associated with a user to generate a user data footprint. The method includes creating reference clusters from the captured user data, identifying, confirming, and rating provenance characteristics of the user data in the created reference clusters. The method includes generating an augmented user data footprint through supplemental user data, including watermark and authorization data on a territory basis, and processing the augmented user data footprint, scoring the same based on industry-specific parameters and weightings, and generating one or more user data registries on an industry-by-industry basis. Thereafter, the method includes enabling transacting of datasets from the one or more user data registries between users supplying data for said datasets and entities desiring to acquire the same.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting a return to a site. In some implementations, a system obtains data indicative of a time evolving movement of a user interacting with a website shown on the client device. The system determines, using a first trained machine learning model and based on the data indicative of the time evolving movement, a metric associated with an emotion of the user corresponding to the user's interaction with the website. The system obtains, from a metric database, metrics associated with an identifier of the user. The system provides, to a second trained machine learning model, (i) the metric associated with the emotion and (ii) data representing the obtained metrics associated with the identifier. The system generates, using the second trained machine learning model, a prediction indicating whether the user is likely to return to the website.

A business support apparatus includes: a parameter storage in which two or more business parameters regarding business are stored; a parameter acquiring unit that acquires business parameters input by a user and accumulates the business parameters in the parameter storage; a response acquiring unit that passes a prompt that is used to acquire a business parameter to generative AI, acquires a response containing the business parameter from the generative AI, and accumulates the business parameter in the parameter storage; a business plan acquiring unit that acquires business plan information on a business plan, using the business parameters in the parameter storage; and a business plan output unit that outputs the business plan information acquired by the business plan acquiring unit.

Systems, apparatuses, methods, and computer program products are disclosed for automatically updating a veteran profile for a user. An example method includes identifying a veteran attribute data field with a data value associated with an unassigned status within a veteran profile of the user. The example method further includes generating a user input data set comprising data instances extracted from user data using a preprocessing model and determining (a) a candidate data value for the veteran attribute data field, and (b) a confidence score for the candidate data value, using an attribute identification model. The example method further includes updating the veteran profile with the candidate data value as the data value for the veteran attribute data field in an instance in which the confidence score satisfies a confidence score threshold. The example method further includes generating and providing a tailored user recommendation based on the veteran profile.

A system and method for utilizing deep learning and machine learning to predict the likelihood of a supplier-buyer relationship existing between two business entities using a retrieval model and a ranking model. The output is a raw supplier propensity score between 0 and 1 representing the likelihood of a supplier-buyer relationship, as well as a propensity class based on ranges of this score. A user-interactive map displays supplier-buyer relationships where the raw supplier propensity score exceeds a threshold value.

A parking lot zone estimating device 30 comprises: a vehicle parking information recording unit 312 for determining that a vehicle is parked if there is no change in positional information for at least a predetermined period of time, and recording, as vehicle parking information, a parking location of the vehicle and a parking time that can be calculated from time information; a parking feature quantity calculating unit 313 for setting, as feature quantities of grids into which a region included in map information is divided, at least one of a parking frequency and a vehicle parking time, calculated on the basis of the vehicle parking information for each grid; and a facility parking lot estimating unit 314 for extracting the grids located within a prescribed range from a facility, and clustering the grids using the feature quantity to identify a parking lot of the facility.

Systems, apparatuses, methods, and computer program products are disclosed for providing a multimodal interactive personal advisor (MIPA). An example method includes retrieving user data associated with a user associated with a living location. The example method also includes retrieving living location data associated with a set of living locations. The example method also includes facilitating an interaction between the user and an MIPA model. The example method also includes extracting, based on the interaction, a set of data features associated with the user and determining, based on the set of data features, second user data. The example method also includes determining, based on the user data and the second user data, a financial status of the user and determining, based on the living location data associated with the set of living locations and the financial status of the user, a second living location for the user.

An object is to provide a recommendation evaluation device capable of evaluating a recommendation. A recommendation system 100 of the present disclosure includes an evaluation derivation unit 103 configured to derive a visit likelihood evaluation g(x) for a store that has been recommended to a target user and a visit likelihood evaluation g(x) assuming that no recommendation has been made, and a recommendation evaluation unit 104 configured to derive a recommendation evaluation on the basis of the visit likelihood evaluation g(x) for the store that has been recommended and the visit likelihood evaluation assuming that no recommendation has been made.