A system and method for home identification is provided. The system selects a set of locations corresponding to a set of calendar dates from user's location history. Each location is associated with a dwell time period which is greater than a first threshold time-period. The system creates a location table by including the set of locations against the set of calendar dates and selects a first location from the location table based on whether a total number of day-wise occurrences of the first location in the location table is above a threshold number in a week period. The system determines a first count of weeks for which the total number of day-wise occurrences of the first location is above the threshold number and determines the first location as a user's home location based on whether the determined first count of weeks is above a threshold number of weeks.

Methods are provided for anonymously tracking and/or analyzing Web-based flow or movement of individual subjects and/or objects. In particular, there is provided a computer-implemented method for enabling anonymous estimation of the amount and/or flow of individuals, in a population moving and/or coinciding between two or more Web-based subject states. The method includes receiving identifying data from two or more individuals; generating, online and by one or more processors, an anonymized identifier for each individual; and storing: the anonymized identifier of each individual together with data representing a Web-based subject state; and/or a skew measure of such an anonymized identifier.

Machine learning (ML) can be used to gather data on prospective customers from publicly available online sources. The ML can provide data on a likelihood of near future, customers and subscribers and a list of people with low interest in the company's products. The ML system can be recursively updated as new public data becomes available online. Thus, the ML system can be used to generate targeted advertising and root cause analysis based on a relationship between people's statuses and their respective interests in certain products and/or services.

Methods, systems, and computer programs are presented for the determination of optimal communication scheduling. One method includes an operation for training a machine-learning program to generate a frequency model that determines a frequency for sending communications to users. The training utilizes training data defined by features related to user information and responses of users to previous communications to the users. The method further includes determining, by the frequency model and based on information about a first user, a first frequency for the first user. The first frequency identifies the number of communications to transmit to the first user per period of time. Further, the method includes operations for receiving a communication request to send one or more communications to the first user and determining send times for the one or more communications to the first user based on the first frequency. The communications are sent at the determined send times.

Systems, devices, and techniques are disclosed for recommendations using a transformer neural network. User activity data including items and actions associated with users and a catalog including descriptions of the items may be received. User vectors for the users, item vectors for the items and action vectors the actions may be generated by applying singular vector decomposition to the user activity data. Sequence vectors may be generated based on item vectors and the action vectors. Transformer vectors may be generated by applying a text-to-text transferring transformer to descriptions of the items. Similarity vectors may be generated based on the transformer vectors. Merged vectors may be generated by merging the sequence vector, transformer vector, and similarity vector for items. A set of probabilities may be determined by inputting the user vector for the user, merged vectors for the items, and sequence vectors for the actions to a transformer neural network.

Disclosed here is a system that can obtain attributes of an advertisement, where an attribute has a continuous value, and a range of acceptable values is uncertain. The system can create a file including contents that when provided to a predetermined function produce a value of the attribute. Based on the file, the system can generate values corresponding to the attributes. Based on the generated values, the system can create the advertisement. The system can obtain a response data to the created advertisement and can fit a multidimensional function to the attributes and the user response data. Based on the multidimensional function, the system can determine next values and next ranges, where the next values and the next ranges indicate an improvement in the response data.

In supply-side information processing apparatus comprising at least one computer processor, a method for providing a user with intent-based ads may include: (1) receiving, from an intent broker, intent identifiers for intent categories of user intents; (2) communicating the intent identifiers to a demand-side platform, the demand-side platform comprising a plurality of advertisers and merchants; (3) receiving, from a supply-side SDK on a user electronic device, personal data for a user, wherein the supply-side SDK captures the personal data from a publisher application executed on the user electronic device; (4) retrieving, based on the personal data and from the intent broker, a user intent identifier for the user, the user intent identifier matching one of the intent categories; (5) communicating the user intent identifier to the supply-side SDK, wherein the supply-side SDK requests an intent-based ad from the demand-side platform using the user intent identifier.

A transaction appliance and techniques for effecting a consumer transaction in a fueling station system is disclosed. Presence of a consumer vehicle at a fuel dispenser is detected and the transaction appliance transmits a transaction trigger to a transaction server located remotely outside the retail fueling station environment. The transaction server responsively invokes personalized consumer data associated with the transaction trigger including advertising and promotions for purchasing products and services from a vendor. The transaction server provides personalized data to a fuel dispenser user interface via the transaction appliance and a user interface system inside the consumer vehicle during a fuel dispensing period.

Systems and methods for a contract-based offer generator is provided. A contract for a promotional offer on a product is received. Data is extracted from the contract. An offer band is accessed, and a plurality of test offers are selected from the offer bank by scoring each offer in the offer bank against the extracted data. The promotional offer and the selected plurality of test offers are deployed in a plurality of retail locations. This is done by maximizing orthogonality between the following variables: store sales, store out of stock rates, number of relevant SKUs carried in each store, temporal effects, discount depth, buy quantity and offer structure.

An information notification method for providing information from a server device to a plurality of devices connected to a network, including: reading notification information stored in association with information indicating a particular action of a user; acquiring operation histories of the plurality of devices; estimating, based on operation histories of one or more devices owned by the user among the plurality of devices, a no-operation period during which the user is unlikely to operate the one or more devices; determining, based on current operation state of the one or more devices, whether the particular action has been performed outside the no-operation period; and transmitting, when outcome of the determining is affirmative, the notification information associated with the particular action to a destination device among the one or more devices owned by the user. The destination device provides the user with the notification information.