Described are systems and methods for providing a multi-tasked trained machine learning model that may be configured to generate product embeddings from multiple types of product information. The exemplary product embeddings may be generated for a corpus of products (e.g., products included in a product catalog, etc.) based on both image information and text information associated with each respective product. Accordingly, the generated product embeddings may be compatible with learned representations of the different types of product information (e.g., image information, text information, etc.) and may be used to create a product index, which can be used to determine and serve product recommendations in connection with multiple different recommendation services that may be configured to receive different types of inputs (e.g., a single image, multiple images, text-based information, etc.).

Methods and apparatus relating to the generation, management and use of taxonomies are described. Over time statistics are collected based on the user interaction and the effectiveness of the taxonomy determined with respect to one or more groups of users. Decisions are automatically made when a new e.g., custom, taxonomy is to be generated for a set of users. Over time multiple custom taxonomies are generated for different user groups with each group of users being provided access to items through the taxonomy which provides the best results for the group. Generated taxonomies are compared and merged or combined when similar to avoid the generation and maintenance of a large number of similar taxonomies.

A search engine provides diverse search results in response to a search query using a trained diversity ranker. The diverse results may be generated by determining ranking positions of at least some search results based on delta feature values that are dependent on higher-ranked results. Delta feature values indicate a degree or magnitude of difference between a particular result and other results with respect to a particular feature, such as price, category, or shipping type. In providing the ranked results for presentation to a user at a computing device, a diversity feature indicator for at least some results may be generated. The diversity feature is a feature that distinguishes a given result from other results. As such, the diversity feature indicator represents that diversity feature for the particular result being different from other results and distinguishes the diversity feature from other features in the particular result.

Disclosed are a method and apparatus for generating information. A method may include: acquiring total number information and initial routing information of a specified item, the initial routing information including current at least one piece of item supply link information and at least one piece of item display link information corresponding to the specified item; querying at least one initial link path between the at least one piece of item supply link information and the at least one piece of item display link information of the initial routing information; determining an updated link path between the at least one piece of item supply link information and the at least one piece of item display link information based on the total number information and the at least one initial link path; and generating and transmitting updated routing information through the updated link path.

In various example embodiments, a system and method for determining a spam publication using a spam detection system are presented. The spam detection system receives, from a device, an image of an item and an item attribute for the item. Additionally, the spam detection system extracts an image attribute based on the received image, and compares the item attribute and the image attribute. Moreover, the spam detection system calculates a confidence score based on the comparison. Furthermore, the spam detection system determines that the item attribute is incorrect based on the confidence score transgressing a predetermined threshold. In response to the determination that the item attribute is incorrect, the spam detection system causes presentation, on a display of the device, of a notification.

Techniques are described for automatically extracting items from a user's browse history on one or more e-commerce websites, and automatically searching other e-commerce websites and sources for offers (including coupons, deals, and/or promotions) for those items and/or related items and/or stores. Such automated techniques allow users to gain the benefit of online offers from various sources, without having to go through the effort of manually searching for such offers. Instead, the system and method automatically locate such offers based on the user's browse history, without requiring any action to be taken on the part of the user.

In some embodiments, apparatuses and methods are provided herein useful to searching retail products for purchase and locations of physical retail stores. In some embodiments, there is provided a system for searching both retail products for purchase and locations of physical retail stores including a user interface; a universal search bar cooperatively operating with the user interface to provide a single search tool for a customer to search one or more databases storing at least retail product inventories and a plurality of retail locations; and a control circuit configured to: receive a communication signal to initiate operation of the user interface.

Systems and methods for guided vehicle matching are disclosed. In order to generate vehicle recommendations for a user of an electronic vehicle listing service, a plurality of vehicle-related lifestyle options are presented to the user, and a user selection received. Additional data regarding the user's vehicle preferences, requirements, or usage may be obtained. Based upon such information, a set of example vehicles is generated and presented to the user. Each example vehicle has characteristics representing a plurality of other vehicles. Based upon user ratings or selections of at least some of the example vehicles, a plurality of vehicle recommendations for specific available vehicles are generated and presented to the user. In some embodiments, further user interaction with such recommendations is used to refine the vehicle recommendations and identify additional vehicle recommendations.

Methods, systems, and computer-readable media are provided for providing information on electronic visual displays in retail stores. In one implementation, a door for a retail storage container may include at least a first part that is configured to face customers when the door is closed and a second part configured to face the internal side of the retail storage container when the door is closed. Further, the second part may include at least an electronic visual display configured to display information, and at least part of the electronic visual display may be configured to be visible to the customers at least when the door is open at a selected angle.

An autonomous futures contract orchestration platform includes a set of processors programmed with a set of non-transitory computer-readable instructions. The instructions include receiving, from a data source, an indication associated with a product that relates to an entity that purchases or sells the product. The instructions include predicting a baseline cost of purchasing or selling the product at a future point in time based on the indication. The instructions include retrieving a futures cost, at a current point in time, of a futures contract for an obligation to the purchasing or selling the product for delivery or performance of the product at the future point in time. The instructions include executing a smart contract for the futures contract based on the baseline cost and the futures cost. The instructions include orchestrating the delivery or performance of the product at the future point in time.