Techniques for detecting and presenting rewards for presence are disclosed. Presence of a mobile device within a building is detected based on a plurality of triggers including a degradation of a first signal and a concurrent improvement of a second signal. The triggers are identified by a client-side application of the mobile device or a corresponding server-side processor with which the client-side application is in communication and from which the client-side application is configured to automatically receive available rewards. In response to detecting presence within the building, the server-side processor determines that a user of the mobile device is eligible for a reward, and the reward is provided to the user via the client-side application at the mobile device.

A system, method, and computer-readable medium are disclosed for management of a distributed ledger technology customer loyalty program, by establishing a distributed ledger technology network of customer and entity nodes. The entity nodes support products and/or services purchased by customers, providing a distributed ledger technology platform accessible by the nodes. Transactions between nodes go through the distributed ledger technology platform. A distributed ledger technology ledger which tracks the transactions. Coins/credits are provided to customers based on their transactions.

An example method includes identifying, using a browser extension, content of a first webpage of a first website being displayed using a browser. The identifying of the content includes determining a product related to the content of the first webpage and determining that the product has been added to an electronic shopping cart. The method further includes determining a merchant that offers the product for sale and determining, based on a user account associated with the browser extension, a customer reward offered by the merchant and available to the user account. The method further includes determining that the browser has navigated away from the first webpage to a second webpage of a second website. The method further includes modifying the browser to display a graphical user interface element including information about the customer reward and a link configured to navigate the browser back to the first website.

Example systems, devices, media, and methods are described for classifying crowdsourced field reports as valid or spam by applying a random forest predictive model. A spam detection system includes an inference engine for generating a feature set based on the data in the field reports, a prediction engine for applying the predictive model to generate confidence scores, and an analytics engine for selecting and executing an action relative to any field report having a confidence score below a predetermined minimum threshold score. The generated feature set includes a social isolation metric associated with a particular user based on a subset of field reports submitted by that user, wherein each field report in the subset represents the only field report associated with a particular place.

The disclosure generally pertains to systems and methods to predict a vehicle preference of a customer of a rental vehicle agency. An example method to do so involves a computer executing a prediction procedure to obtain and evaluate information associated with a customer. The information can include vehicle ownership history and/or monitoring data obtained from vehicles used by the customer (a personal vehicle, a taxi, and/or a ride share service vehicle, for example). The information may be evaluated by the computer to determine a personal profile of the customer. The personal profile can include items such as physical attributes of the customer, family size, driving characteristics, and/or past vehicle ownership. The personal profile of the customer may then be used by the computer to predict a type of vehicle preferred by the customer and to select, from a vehicle fleet, a vehicle that matches the preferred type of vehicle.

A method including receiving a digital promotion payload from a brand manufacturer for at least one branded consumer packaged good, the digital promotion payload including a digital promotion value associated with the branded consumer packaged good, is provided. The method includes receiving a bid request to the digital promotion engine, providing a bid response to the bid request, the bid response including the digital promotion payload, and receiving, from the supply side platform, a confirmation that the bid response has been selected from one or more bids from different digital advertising entities. The method includes providing a command to the supply side platform to deliver the digital promotion payload to a mobile device accessing a resource from the mobile display publisher, and loading the digital promotion value to a frequent shopper identification in response to a consumer interaction with the digital promotion payload detected from the mobile device.

In general, embodiments of the present invention provide systems, methods and computer readable media for a predictive recommendation system based on an analysis of previous consumer behavior. One aspect of the subject matter described in this specification can be embodied in methods that include the actions of receiving data representing a user, the data including user identification and historical data; receiving a set of promotions recommended for the user; assigning the user to a consumer lifecycle model state based in part on the historical data and the user identification; selecting a ranking algorithm associated with the consumer lifecycle model state; and ranking the received set of promotions based on a predicted promotion relevance value associated with each promotion, the predicted promotion value being calculated using the ranking algorithm.

Systems, apparatuses, and methods are described for determining a consumer's engagement with a brand of the business by tracking the consumer's activities in multiple platforms, such as social media platforms, content platforms, gaming platforms, other retailers, streaming video providers, service providers, etc. Method are described for probabilistically granting users variations of items that are otherwise being acquired. The granting may be random, but probabilities may be boosted based on the consumer's activities in the platforms.

Techniques and arrangements for performing data analysis in order to generate connections between merchants. For instance, a payment service may determine, based at least in part on transaction information, that a first customer conducted a first transaction at a first merchant followed a subsequent transaction at a second merchant. The payment service may further determine that a second customer conducted a second transaction at the first merchant followed by a subsequent transaction at a third merchant, Based on transaction information associated with the first transaction and the second transaction, the payment service may create a buyer profile including the first customer and second customer. Upon the payment service receiving a request to process a third transaction between the first merchant and the second customer, the payment service can generate a recommendation that the second customer conduct a subsequent transaction to the third transaction at the second merchant rather than the third merchant. The payment service can then send a electronic communication that includes the recommendation to the first merchant or the second customer.

A fleet management system implements a rewards-based feedback system to receive feedback from users of a rideshare service that provides rides using autonomous vehicles (AVs). The fleet management system maintains user accounts associated with each user and provides reward points to each user account. When the user is riding in an AV, the user can access a user interface to select a portion of the reward points and reward them to the AV. The fleet management system may analyze the point rewards to identify individual user preferences, to identify preferences across users, or to identify AVs for maintenance or other types of modification.