Systems and methods are provided for generating and provisioning personalized news feeds for athletes. One embodiment is a system that receives metrics for exercise activities performed by athletes. The system generates records of the exercise activities of the athletes based on the metrics, determines a type of exercise for each record, classifies the records based on corresponding types of exercise, and compiles a fitness history, for each athlete, comprising records of exercise activities performed by the athlete. For each of the athletes, the system generates a digital news feed for the athlete, identifies categories of engagement for the athlete based on types of exercise indicated in the fitness history of the athlete, selects articles from a repository, personalizes the digital news feed for the athlete by populating the digital news feed with the selected articles, and transmits the digital news feed to a user device.

Described is a system for learning and predicting key phrases. The system learns based on a dataset of historical forecasting questions, their associated time-series data for a quantity of interest, and associated keyword sets. The system learns the optimal policy of actions to take given the associated keyword sets and the optimal set of keywords which are predictive of the quantity of interest. Given a new forecasting question, the system extracts an initial keyword set from a new forecasting question, which are perturbed to generate an optimal predictive key-phrase set. Key-phrase time-series data are extracted for the optimal predictive key-phrase set, which are used to generate a forecast of future values for a value of interest. The forecast can be used for a variety of purposes, such as advertising online.

Described herein is a system and techniques for implementing a system that enables exchange of user information between retail and advertising domains while maintaining data security and privacy requirements. In some embodiments, a landing page is generated in response to a user interaction with a user interface element. The landing page is generated within the retail domain while the advertisement is in an advertising domain. The landing page, while in the retail domain, can access stored user information from the retail website and pre-fill forms of the landing page which a user can verify and submit to the advertising, thereby sharing the user information into the advertising domain.

The purpose of the present invention is to make it possible to provide related content to a terminal of a consumer who purchased a commercial product from any shop. A purchase information utilization system includes: a storage unit which stores a shop and content in association with each other; a receiving unit which receives information related to a receipt from a terminal of a consumer; an analysis unit which analyzes the information related to the receipt to identify a shop from which the consumer purchased a commercial product; and a content providing unit which extracts content related to the identified shop from the storage unit, and provides the extracted content to the terminal.

An item proposal system proposes an appropriate item even to a user accessing a website for the first time. A D/B 8 accumulates reference information in which a reference item, a reference phrase, and a reference attribute as an attribute of a target customer are associated with each other. Pieces of reference information having the same reference phrase constitute an information group. An extraction unit 31 extracts a user phrase based on record information acquired from a terminal 3. An information group detection unit 32 detects an extraction information group corresponding to a reference phrase that matches the user phrase. An item proposal unit 34 selects, as a proposed item, a reference item of a non-extraction information group that is an information group other than the extraction information group and whose reference attribute correlates with a reference attribute of the extraction information group.

In general, embodiments of the present invention provide systems, methods and computer readable media for a predictive recommendation system using predictive models derived from tiered feature data.

An information processing apparatus comprises: an acquisition unit that acquires information indicating a featured product including a product of interest to a customer visiting a store; and an output unit that outputs ranking information, that satisfies a first criterion, regarding a sales performance of the featured product and regarding a parameter.

A synthesized, advertisement-based, video stream is generated first by receiving a video stream essentially consisting of a representative image of a person, a video stream comprising a place, and a video stream comprising an advertisement, and then combining the video stream essentially consisting of the representative image of the person with the video stream comprising the place and with the video stream comprising the advertisement into the synthesized, advertisement-based, video stream for transmission to an end-user device via which to display the synthesized, advertisement-based, video stream.

A subscription-based system for providing commerce information for one or more mobile devices for one or more merchants. Some techniques employed feature a subscription-based method for presenting commercial resources to a mobile device. The method involves receiving mobile device user information relating to a geographic location to locate one or more merchants within a subscription-based shopping network, and receiving mobile device user information relating to a merchant type within the subscription-based shopping network. The method also involves receiving, from a database over a communication network, information for one or more merchants associated with the mobile device user information for the geographic location and the merchant type, and presenting the associated merchant information on the mobile device. The associated merchant information can include a merchant name and address, a merchant telephone number, a merchant advertisement, a merchant coupon, or a merchant product or service offering to subscribers of the shopping network.

A digital brand asset system performs the steps of providing payloads for a smart brand asset to a plurality of web servers which include codes representing the smart brand asset, receiving feedbacks on how the smart brand asset is presented on the website servers, collecting web journey data of the website visitors' who have interacted with the smart brand asset, generating a report detailing how effective the smart brand asset has been on the website servers, and presenting the report on a dashboard. Generally, by monitoring the website servers and visitors interacting with the smart brand assets, a report can be generated for the brand owners to determine the effectiveness of the smart brand assets hosted on the website servers. The raw data used to generate the report can be used to autonomically and dynamically change the content based upon the interpretation of the feedbacks.