Techniques are disclosed utilizing cognitive computing to improve banking experiences. A user's financial account(s) and location may be monitored to predict when a user is near a retail store and the user has not used a particular account in a predetermined amount of time. The techniques disclosed include receiving a location for a user's mobile device, and determining when the mobile device is within a predetermined threshold distance of a retail store. The techniques include building a shopping profile for the user based upon shopping habits for the user. The shopping profile may be used to determine what commercial communications should be transmitted to the user to encourage them to utilize an inactive account to make a purchase at the retail store when the user is within the threshold distance of the retail store.

An online system trains a machine-learned lift prediction model configured as a neural network. The machine-learned lift prediction model can be used during the inference process to determine lift predictions for users and items associated with the online system. By configuring the lift prediction model as a neural network, the lift prediction model can capture and process information from users and items in various formats and more flexibly model users and items compared to existing methods. Moreover, the lift prediction model includes at least a first portion for generating control predictions and a second portion for generating treatment predictions, where the first portion and the second portion share a subset of parameters. The shared subset of parameters can capture information important for generating both control and treatment predictions even when the training data for a control group of users might be significantly smaller than that of the treatment group.

A method and system for collecting and sharing real estate listings and home related content from a web browser, web application or mobile application. A browser extension or mobile app permits a user to save selected real estate listings on an account at a remote server. The user can then review all of the saved real estate listings in a personalized summary page, share the page with others, and get feedback from others. The server may suggest additional listings to the user based upon the saved selections and may learn from the user's reaction to the suggested listings.

The present disclosure relates systems and methods for food recommendations. More particularly, it teaches a systems and methods that can provide personalized menu item recommendations through a nutrient-focused machine learning model for nearby restaurants in near real-time, in order to assist in the selection of dishes that match a user's persona. Using these systems and methods enable a user to see a personalized prediction score of how much the system predicts that a particular user would like a particular dish.

Demographic assessment of information is facilitated using targeted location oversampling. In one example, a device determines mobile devices communicatively coupled to a base station device associated with a first defined region, wherein the first defined region is relative to a defined location of interest. The device can transmit a set of instructions to the mobile devices that instruct the mobile devices to power on respective location information components configured to transmit location information. The respective location information can be configured to transmit respective global positioning system information for the mobile devices. The device can also determine which ones of the mobile devices are within a second defined region based on respective location information received from the mobile devices.

Systems and methods are described for location modeling in hybrid last-mile deliveries. Hybrid last-mile delivery may refer to delivery of items in which a delivery vehicle meets customers at a pickup location at a specified time. Thus, instead of conventional last-mile delivery in which a delivery vehicle delivers items to an end point, such as a customer home, customers are to meet the delivery vehicle at a specified location and time to pick up items. The systems and methods described herein may include computational modeling of locations to identify or select pickup locations for hybrid last-mile delivery. Such modeling may include rules-based and/or machine-learning models for identifying or selecting pickup locations.

Techniques for suggesting targeting criteria for a content delivery campaign are provided. An affinity score representing an affinity between the attribute values of each pair of multiple pairs of attribute values is computed. First input indicating a particular attribute value for a particular attribute type is received through a user interface for creating a content delivery campaign. The user interface includes fields for inputting attribute values for multiple attribute types that includes the particular attribute type. In response to the first input and based on affinity scores associated with the particular attribute value, a set of suggested attribute values is identified. The user interface is updated to include the set of suggested attribute values. Second input indicating a selection of a particular suggested attribute value is received. The particular suggested attribute value is added to the content delivery campaign.

Systems, methods and computer program products for selecting dealers based on characteristics of the dealers and the user. A vehicle data system collects dealer location and historical transaction data from external data sources and generates and stores an eligibility table that identifies a set of eligible dealers for each combination of user location and vehicle make. Eligible dealers are determined from the eligibility table using a location and vehicle make identified from a user request. Scores are determined for each eligible dealer based on a dealer scoring model using a binary choice model in the form of a logistic regression of market share, inventory, close rate, price and distance, and dealers are ranked by these scores. A presentation of dealers selected by rank and by closest location to the user is generated and provided to the user via an interface running on a computing device.

A method for providing information based on geographic parameters is disclosed. The method includes providing a map. A user-defined position on the map is received. Data of a first type, wherein the first type data relates to the user-defined position on the map, is provided.

In accordance with one or more aspects of selecting between client-side and server-side market detection, a determination is made at a device as to which of a client-side detected market and a server-side detected market is to have priority for a service. An application of the device is configured in accordance with a client-side market configuration setting if the client-side detected market has priority, and is configured in accordance with a server-side market configuration setting if the server-side detected market has priority.