An electronic commerce platform application server comprises a digital closet application, a sell-to-buy application, and a machine learning system. The digital closet application allows users to efficiently digitize and virtually store their physical items. The digital closet application receives sensor data, such as an image or point cloud data, and detects the item and predicted sale value using a machine learning system. Digital closet items are viewed and managed via a digital closet interface, which provides images, attributes, and descriptive information of each item. The digital closet interface is dynamically updated to present marketplace insights to users based on their items and optimal sale periods based on triggers, upcoming events, and configurable thresholds. The sell-to-buy application allows a user to trade-in one or more items in exchange for credit towards a new item available on the electronic commerce platform and utilizes user interaction information to prompt trade-ins during optimal times.

Disclosed herein are methods and systems for generating a customized online environment for procuring products. The method includes extracting an account identifier from procurement history data for an entity, where the account identifier is associated with a third-party system. The method further includes generating a profile with the third-party system and associating the profile with the account identifier. Next, an online environment is generated that lists or displays at least one product associated with the third-party system for procurement thereof. The method further includes receiving a request, via the online environment, from the entity to procure the at least one product. Finally, the method includes accessing the profile on the third-party system and submitting a procurement request for the at least one product.

A computer-implemented method and system for providing personalized style recommendations in a social shopping environment are described. The method involves searching for a wardrobe associated with a specific person, identifying styles, and generating virtual fit pics for users. These virtual fit pics allow users to see digital representations of themselves wearing clothing items and include interactive elements for purchasing. Users can follow specific wardrobes, which are displayed in their content streams, and receive updates with new digital representations or clothing items. The system comprises a remote storage system, a personal stylist agent, a user interface, and a social wardrobe feed, all working together to enhance the shopping experience.

An arrangement for managing embedded content it is provided. The arrangement is able to provide relevant embedded content to different websites and applications without having direct input in form of cookies. The content management arrangement uses contextual targeting using a large dataset comprising contextually classified data. The classified data is then used in contextual targeting based on the context of the content requesting embedded content.

This food recommendation system includes: an acquisition unit that acquires in advance event data including identification information of a food eaten by a user, food type information including taste sensation information for classifying the food by taste sensation, and mealtime information; an extraction unit that calculates, by a time-series association analysis, a characteristic index including at least one of a support degree, a reliability degree, and a lift value related to the dietary habit of the user on the basis of the event data, and extracts a specific characteristic index corresponding to specific food type information input by the user; and a recommendation unit that outputs a food candidate that is proposed to the user on the basis of the specific characteristic index.

A method and server for generating user recommendations for users of a digital recommendation platform are provided. The method comprises: generating, by scanning a chronologically organized user log, a training set of data comprising a plurality of training digital objects; and feeding each one of the plurality of training digital objects to the MLA, thereby causing the MLA to generate a respective predicted indication of the user interaction of a given user with a given digital item of the digital recommendation platform; and applying a loss function, configured to penalize the respective predicted indication if it is different from the respective label, thereby training the MLA to identify, in a plurality of digital items of the digital recommendation platform, for the given user, the previously unseen digital items associated with the previously unknown, for the given user, source with which the given user is likely to interact.