Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data is then received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: A method of training a machine learning model to determine an item margin is provided. The method includes monitoring a first value for a first item having attributes and monitoring a first value for a second type of item having attributes where an attribute of the first attributes is the same as an attribute of the second attributes. The method also includes determining a first margin based on the first values. The first attributes, the second attributes, and the first margin are input as training data for the machine learning model where the machine learning model is trained with the training data. The monitoring operations for the first item and the second item are repeated to obtain a second value for the first and second items. Furthermore, the trained machine learning model is applied to the second values to determine a second margin.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

Abstract: A method of training a machine learning model to determine an item margin is provided. The method includes monitoring a first value for a first item having attributes and monitoring a first value for a second type of item having attributes where an attribute of the first attributes is the same as an attribute of the second attributes. The method also includes determining a first margin based on the first values. The first attributes, the second attributes, and the first margin are input as training data for the machine learning model where the machine learning model is trained with the training data. The monitoring operations for the first item and the second item are repeated to obtain a second value for the first and second items. Furthermore, the trained machine learning model is applied to the second values to determine a second margin.

Abstract: Systems and methods for processing webpage calls via multiple module responses are described. A system may receive, from a client device, a first call for module data associated with a set of webpage modules for presentation in a webpage. The system may subsequently transmit, to the client device based on receiving the first call, a first response including first module data associated with a first subset of the set of webpage modules. The first response may additionally include a token identifying the webpage. The server may additionally transmit, to the client device based on transmitting the first response, a second response including the token identifying the webpage and second module data associated with a second subset of the set of webpage modules that differs from the first subset of the set of webpage modules.

Abstract: Methods for determining which image of a set of images to present in a search results page for a product are described. Components of a server system may receive a set of images for a set of items associated with a product. Components of the server system may perform image ranking to rank the set of images to identify a representative image of the set of images for the product, based on a user interaction metric of each image of the set of images. The components of the server system may then receive, from a user device, a search query that may be mapped to the product, and the component of the server system may transmit, to the user device, the search results page that includes at least one item of the set of items and the representative image based on the interaction metric of the representative image.

Abstract: Systems and methods for processing webpage calls via multiple module responses are described. A system may receive, from a client device, a first call for module data associated with a set of webpage modules for presentation in a webpage. The system may subsequently transmit, to the client device based on receiving the first call, a first response including first module data associated with a first subset of the set of webpage modules. The first response may additionally include a token identifying the webpage. The server may additionally transmit, to the client device based on transmitting the first response, a second response including the token identifying the webpage and second module data associated with a second subset of the set of webpage modules that differs from the first subset of the set of webpage modules.

Abstract: A system for assisting users in listing items for sale in an electronic marketplace is disclosed. A video is received from a user device associated with a user, the video including a video stream depicting a plurality of items to be listed for sale in the electronic marketplace. Respective images depicting respective items among the plurality of items are obtained from the video stream, and respective attributes of the respective items among the plurality of items are extracted from the video. Respective listings for sale of the respective items are generated based at least in part on the respective attributes of the respective items among the plurality of items, and the respective listings for sale of the respective items are displayed to the user.

Abstract: A method of training a machine learning model to determine an item margin is provided. The method includes monitoring a first value for a first item having attributes and monitoring a first value for a second type of item having attributes where an attribute of the first attributes is the same as an attribute of the second attributes. The method also includes determining a first margin based on the first values. The first attributes, the second attributes, and the first margin are input as training data for the machine learning model where the machine learning model is trained with the training data. The monitoring operations for the first item and the second item are repeated to obtain a second value for the first and second items. Furthermore, the trained machine learning model is applied to the second values to determine a second margin.

Abstract: A first test case identifier that indicates a first test case is received. The first test case is indicative of testing one or more features of an application associated with the electronic marketplace. The first test case identifier is compared to a plurality of attributes. The plurality of attributes are associated with one or more listings that describe one or more items for sale in an electronic marketplace. Based at least in part on the comparing, it is determined that a first set of attributes, of the plurality of attributes, are test data candidates to be used as input to the first test case. Based at least in part on the determining, the first test case is caused to be run using at least one of the first set of attributes as test data for input.

Abstract: Techniques are disclosed for automatically adjusting machine learning parameters in an e-commerce system. Hyperparameters of a machine learning component are tuned using a gradient estimator and a first training set representative of an e-commerce context. The machine learning component is trained using the tuned hyperparameters and the first training set. The hyperparameters are automatically re-tuned using the gradient estimator and a second training set representative of a changed e-commerce context. The machine learning component is re-trained using the re-tuned hyperparameters and the second training set.

Abstract: Different action user-interface components in a comparison view are described. Initially, a selection is received to display a comparison view via a user interface of a listing platform. Multiple listings of the listing platform are selected for inclusion in the comparison view. A comparison view system determines which action of a plurality of actions, used by the listing platform, to associate with each of the listings. A display device displays the multiple listings concurrently in a comparison view via a user interface of the listing platform and also displays an action user-interface component (e.g., a button) in each of the plurality of listings. The action user-interface component is selectable to initiate the action associated with the respective listing. In accordance with the described techniques, the action user-interface component displayed in at least two of the multiple listings is selectable to initiate different actions in relation to the respective listing.

Abstract: Technologies are shown for artificial intelligence agents for predicting items of interest utilizing multiple data sources, such as historical user behavior, item wear profiles, inventory data and social network data. User models to the multiple sources of data to predict an item of interest to the user. Search requests pertaining to the predicted item can be generated and submitted to electronic commerce platforms and results responsive to the first set of search requests pertaining to the first predicted item received. In one aspect, one or more of the search results can be selected for display to the user. A search result selected by the user can be received and a purchase transaction committed. In another aspect, the agent is authorized to autonomously execute a purchase transaction on a selected one of the search results. Different model types can be utilized for predicting different types of items.

Abstract: Different action user-interface components in a comparison view are described. Initially, a selection is received to display a comparison view via a user interface of a listing platform. Multiple listings of the listing platform are selected for inclusion in the comparison view. A comparison view system determines which action of a plurality of actions, used by the listing platform, to associate with each of the listings. A display device displays the multiple listings concurrently in a comparison view via a user interface of the listing platform and also displays an action user-interface component (e.g., a button) in each of the plurality of listings. The action user-interface component is selectable to initiate the action associated with the respective listing. In accordance with the described techniques, the action user-interface component displayed in at least two of the multiple listings is selectable to initiate different actions in relation to the respective listing.

Abstract: Techniques for prefetching operation cost based digital content and digital content with emphasis that overcome the challenges of conventional systems are described. In one example, a computing device may receive digital content representations of digital content from a service provider system, which are displayed on a user interface of the computing device. Thereafter, the computing device may also receive digital content as prefetches having a changed display characteristic as emphasizing a portion of the digital content based on a model trained using machine learning. Alternatively, the computing device may receive digital content as a prefetch based on a model trained using machine learning in which the model addresses a likelihood of conversion of a good or service and an operation cost of providing the digital content. Upon receiving a user input selecting one of the digital content representations, digital content is rendered in the user interface of the computing device.

Abstract: Systems and methods for processing webpage calls via multiple module responses are described. A system may receive, from a client device, a first call for module data associated with a set of webpage modules for presentation in a webpage. The system may subsequently transmit, to the client device based on receiving the first call, a first response including first module data associated with a first subset of the set of webpage modules. The first response may additionally include a token identifying the webpage. The server may additionally transmit, to the client device based on transmitting the first response, a second response including the token identifying the webpage and second module data associated with a second subset of the set of webpage modules that differs from the first subset of the set of webpage modules.

Abstract: A first test case identifier that indicates a first test case is received. The first test case is indicative of testing one or more features of an application associated with the electronic marketplace. The first test case identifier is compared to a plurality of attributes. The plurality of attributes are associated with one or more listings that describe one or more items for sale in an electronic marketplace. Based at least in part on the comparing, it is determined that a first set of attributes, of the plurality of attributes, are test data candidates to be used as input to the first test case. Based at least in part on the determining, the first test case is caused to be run using at least one of the first set of attributes as test data for input.

Abstract: Techniques for prefetching operation cost based digital content and digital content with emphasis that overcome the challenges of conventional systems are described. In one example, a computing device may receive digital content representations of digital content from a service provider system, which are displayed on a user interface of the computing device. Thereafter, the computing device may also receive digital content as prefetches having a changed display characteristic as emphasizing a portion of the digital content based on a model trained using machine learning. Alternatively, the computing device may receive digital content as a prefetch based on a model trained using machine learning in which the model addresses a likelihood of conversion of a good or service and an operation cost of providing the digital content. Upon receiving a user input selecting one of the digital content representations, digital content is rendered in the user interface of the computing device.

Abstract: Systems and methods for processing webpage calls via multiple module responses are described. A system may receive, from a client device, a first call for module data associated with a set of webpage modules for presentation in a webpage. The system may subsequently transmit, to the client device based on receiving the first call, a first response including first module data associated with a first subset of the set of webpage modules. The first response may additionally include a token identifying the webpage. The server may additionally transmit, to the client device based on transmitting the first response, a second response including the token identifying the webpage and second module data associated with a second subset of the set of webpage modules that differs from the first subset of the set of webpage modules.

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.