Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing a plurality of parameters of a black box system with respect to a distribution of the plurality of parameters are disclosed. Methods can include obtaining a fitness function of the black box system and a training dataset including multiple training samples. Methods can further include training an ensemble of machine learning model wherein during each iteration of the training process an output of the system is generated for each of the multiple training samples. During each iteration, a predictive value is also generated using an ensemble of machine learning models. A natural gradient is determined based on the output of the system and the predictive value. The ensemble of machine learning models is then trained using the natural gradient.

Abstract: A unified system with a machine learning feature data pipeline that can be shared among various product areas or teams of an electronic platform is described. A set of features can be fetched from multiple feature sources. The set of features can be combined with browsing event data to generate combined data. The combined data can be sampled to generate sampled data. The sampled data can be presented in a format having a structure that is agnostic to a feature source from which the set of features was fetched. The sampled data can be joined with old features by a backfilling process to generate training data designed to train one or more machine learning models. Related methods, apparatuses, articles of manufacture, and computer program products are also described.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on a computer storage medium, that rank items based on user interactions within the same web session. The method includes: providing a first content page for display on a client device; receiving a set of user interactions with one or more items of the first plurality of items; determining an affinity score representing a user interest in the attribute based on the set of user interactions; updating an attribute repository storing a second plurality of attributes and corresponding current affinity scores; identifying a second plurality of items and a corresponding third plurality of attributes; ranking the second plurality of items; and providing a second content page for display on the client device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for imbalance detection in online experiments. In some implementations, a method includes obtaining user information indicating a first set of devices assigned a first version of a service and a second set of devices assigned a second version of the service in a multivariate testing framework; generating alternative samplings of devices; generating a threshold for detecting imbalance using the alternative samplings of devices, a generated expected first set of devices, and a generated expected second set of devices; detecting an imbalance using the obtained user information indicating the first set of devices, the second set of devices, and the generated threshold; and implementing a corrective action to mitigate the detected imbalance in the multivariate testing framework.

Abstract: Aspects of the disclosure provide a computer-implemented method for generating personalized results. The method includes identifying a set of user actions by a specific user within a sliding window of time, generating a first representations for the set of user actions using an encoder component of a personalization module, generating a second representation for the set of user actions using a pretrained representations component of the personalization module, generating a third representation for the set of user actions using a learned representations component of the personalization module, using the personalization module to combine the first representation, second representation and the third representation to generate a short-term personalized representation for the specific user, and providing a set of results for display to the user based on the short-term personalized representation.

Abstract: A method of shopping within an electronic commerce environment includes enabling a first user of a plurality of users to add one or more items to a virtual shopping cart of the first user that is maintained by a server computer system, generating, by the server computer system, statistical data related to the one or more items, and providing the statistical data to the first user in a web page that is generated by the server computer system. The statistical data includes a total quantity of at least one of the one or more items that are contained in the virtual shopping carts of all of the plurality of users.

Abstract: The technology involves a personalized recommender system that can be used with an e-commerce platform. It employs a contrastive learning based cross-domain recommendation approach. The approach balances the learning of user behaviors within each domain, as well as user behaviors across multiple domains. To achieve robust user representations and to improve knowledge transfer between the source and target domains, multi-task intra-domain contrastive regularizations may be employed along with multiple branches of sequential attentive encoders in a model for cross-domain sequential recommendation. Different data augmentation approaches can be used to generate augmented data for contrastive learning. For instance, different data augmentation methods may be combined with recommendation optimization in a multi-task learning paradigm. An optimized sequence representation may be fine-tuned in a next-value prediction task for recommendation in a target domain.

Abstract: Methods, systems, and computer readable medium for a multi-source item creation system. The method includes receiving, through a user interface and from a requesting member of a digital platform, manufacturing parameters for an item to be manufactured, dynamically altering the user interface based on the manufacturing parameters to include different user interface elements that correspond to a subset of attributes, determining, based on interaction with the different user interface elements, additional manufacturing parameters, generating, using one or more machine learning models, a set of manufacturers based on the manufacturing parameters and the additional manufacturing parameters, wherein the one or more machine learning models have been trained to generate the set of manufacturers based on a level of uniqueness of the item to be manufactured and characteristics of the manufacturers, and returning, to the requesting member, a subset of the set of manufacturers.

Abstract: An on-line marketplace provides systems and methods for a mutually beneficial messaging campaign with one or more merchants, in order to promote the merchants' products. One aspect of the messaging campaign includes augmenting the merchants' budgets across multiple commercial channels. The channels may include merchant-operated channels, marketplace-operated channels, and/or third party channels. The marketplace selects when and how to augment the merchants' budgets. The augmented budget comprises an overall content budget for the messaging campaign, including a first budget portion provided by the merchant(s) and a second budget portion provided by the on-line marketplace. The augmented budget may be determined based on a weighted combination of goals of the marketplace and one or more merchants. The augmented budget may be segmented into static and dynamic portions, in which the dynamic portion is varied between channels to determine variables to optimize budget allocation and message performance.

Abstract: Indexing data is disclosed. An image and a text data associated with a dataset are received. A tag is generated using one or more hierarchical classifiers. The image and the text data are input into at least one of the one or more hierarchical classifiers. A search index is generated based at least on the generated tag.

Abstract: A system and method for selling product is provided. In accordance with one aspect, shoppers using an Internet-based commerce site may request custom designed products rather than mass produced products from willing sellers. Shoppers may provide terms under which the custom good must be manufactured. Various systems and methods may also provide a platform for shoppers and sellers to negotiate terms and/or to incorporate negotiated terms into such requests. According to some embodiments, the system and method for selling product facilitates fabrication, delivery and payment for customized goods. In one embodiment, requests for customized goods may be fulfilled by multiple sellers. One example includes multiple sellers fulfilling a custom request, and another includes multiple sellers each producing a part of a desired quantity for a custom request, among other options. One aspect also includes allowing shoppers to request custom made products from one or more manufacturers.

Abstract: This specification relates to methods and systems for providing intuitive navigation of a set of entities. One of the methods includes determining n-dimensional embeddings representing entities; reducing the n-dimensional embeddings representing entities into a 2-dimensional representation of the entities; forwarding, for display on a user's computing device, the 2-dimensional representation of the entities; receiving an input from the user's computing device; responsive to the input, determining an additional 2-dimensional entity representation; and forwarding, for display on the user's computing device, the additional 2-dimensional entity representation.

Abstract: An on-line marketplace provides systems and methods for a mutually beneficial messaging campaign with one or more merchants, in order to promote the merchants' products. One aspect of the messaging campaign includes augmenting the merchants' budgets across multiple commercial channels. The channels may include merchant-operated channels, marketplace-operated channels, and/or third party channels. The marketplace selects when and how to augment the merchants' budgets. The augmented budget comprises an overall content budget for the messaging campaign, including a first budget portion provided by the merchant(s) and a second budget portion provided by the on-line marketplace. The augmented budget may be determined based on a weighted combination of goals of the marketplace and one or more merchants. The augmented budget may be segmented into static and dynamic portions, in which the dynamic portion is varied between channels to determine variables to optimize budget allocation and message performance.

Abstract: An enhanced ranking approach is used to evaluate selected metrics for various services, including search and recommendations for online marketplaces and other search engine-related applications. This includes a ranking system capable of learning neural networks which efficiently tradeoff between different business objectives. For instance, a hybridized ranking system combines the strength of relevancy focused models with the flexibility of ES via ensembling to solve multi-objective ranking problems.

Abstract: An on-line marketplace provides systems and methods for a mutually beneficial messaging campaign with one or more merchants, in order to promote the merchants' products. One aspect of the messaging campaign includes augmenting the merchants' budgets across multiple commercial channels. The channels may include merchant-operated channels, marketplace-operated channels, and/or third party channels. The marketplace selects when and how to augment the merchants' budgets. The augmented budget comprises an overall content budget for the messaging campaign, including a first budget portion provided by the merchant(s) and a second budget portion provided by the on-line marketplace. The augmented budget may be determined based on a weighted combination of goals of the marketplace and one or more merchants. The augmented budget may be segmented into static and dynamic portions, in which the dynamic portion is varied between channels to determine variables to optimize budget allocation and message performance.

Abstract: Methods, systems, and computer readable medium for a multi-source item creation system. The method includes receiving, through a user interface and from a requesting member of a digital platform, manufacturing parameters for an item to be manufactured, dynamically altering the user interface based on the manufacturing parameters to include different user interface elements that correspond to a subset of attributes, determining, based on interaction with the different user interface elements, additional manufacturing parameters, generating, using one or more machine learning models, a set of manufacturers based on the manufacturing parameters and the additional manufacturing parameters, wherein the one or more machine learning models have been trained to generate the set of manufacturers based on a level of uniqueness of the item to be manufactured and characteristics of the manufacturers, and returning, to the requesting member, a subset of the set of manufacturers.

Abstract: A method of shopping within an electronic commerce environment includes enabling a first user of a plurality of users to add one or more items to a virtual shopping cart of the first user that is maintained by a server computer system, generating, by the server computer system, statistical data related to the one or more items, and providing the statistical data to the first user in a web page that is generated by the server computer system. The statistical data includes a total quantity of at least one of the one or more items that are contained in the virtual shopping carts of all of the plurality of users.

Abstract: A computer-implemented method includes receiving a search query from a user through a user interface of a user computing device, identifying a search term within the search query, the search term including at least a portion of the search query, generating, based at least in part on the search term, one or more alternative search terms that are each different from the search term, and sending, over the communication network, the one or more alternative search terms to the user computing device.

Abstract: This specification relates to methods and systems for providing intuitive navigation of a set of entities. One of the methods includes determining n-dimensional embeddings representing entities; reducing the n-dimensional embeddings representing entities into a 2-dimensional representation of the entities; forwarding, for display on a user's computing device, the 2-dimensional representation of the entities; receiving an input from the user's computing device; responsive to the input, determining an additional 2-dimensional entity representation; and forwarding, for display on the user's computing device, the additional 2-dimensional entity representation.

Abstract: An on-line marketplace provides systems and methods for a mutually beneficial messaging campaign with one or more merchants, in order to promote the merchants' products. One aspect of the messaging campaign includes augmenting the merchants' budgets across multiple commercial channels. The channels may include merchant-operated channels, marketplace-operated channels, and/or third party channels. The marketplace selects when and how to augment the merchants' budgets. The augmented budget comprises an overall content budget for the messaging campaign, including a first budget portion provided by the merchant(s) and a second budget portion provided by the on-line marketplace. The augmented budget may be determined based on a weighted combination of goals of the marketplace and one or more merchants. The augmented budget may be segmented into static and dynamic portions, in which the dynamic portion is varied between channels to determine variables to optimize budget allocation and message performance.