Abstract: In various exemplary embodiments, a system and associated method to perform an adaptive risk-based assessment of a user is disclosed. A method includes receiving a request from a user to perform an action at an electronic marketplace, retrieving a plurality of risk assessment factors associated with the action and the user, performing a risk assessment process on the risk assessment factors to identify a risk mitigation process, requesting that the user perform the identified risk mitigation process, and allowing the user to perform the action in response to the user completing the risk mitigation.

Abstract: Systems and methods for providing a service experience score at a merchant physical location include a system provider device that determines, through communication at least one of a plurality of beacon devices located at the merchant physical location and a user device, a start of a user service experience. The system provider device also determines, through the at least one of the plurality of beacon devices and the user device, an end of the user service experience. A service experience score that is based at least partly on the start of the user service experience and the end of the user service experience is generated. The service experience score is stored in a database in association with a merchant that is associated with the merchant physical location. Subsets of the service experience score may be associated with different locations of the merchant physical location.

Abstract: A system to receive data indicative of physical location from a first computing device and to associate an event with the physical location, the event occurring at the physical location and including the physical presence of two or more entities. The system further to receive registration information from one or more entities that are associated with the event and to generate, using the registration information, a data object to enable a first entity of the one or more entities and a second entity of the one or more entities to exchange one or more items while the first entity and the second entity are both physically present at the event. The system additionally to publish the data object to a second computing device based on a participation criteria, the second device being operated by at least one of the first entity and the second entity.

Abstract: Systems, methods, and computer program products for identifying a relevant candidate product in an electronic marketplace. Embodiments perform a visual similarity comparison between candidate product image visual content and input query image visual content, process formal and informal natural language user inputs, and coordinate aggregated past user interactions with the marketplace stored in a knowledge graph. Visually similar items and their corresponding product categories, aspects, and aspect values can determine suggested candidate products without discernible delay during a multi-turn user dialog. The user can then refine the search for the most relevant items available for purchase by providing responses to machine-generated prompts that are based on the initial search results from visual, voice, and/or text inputs. An intelligent online personal assistant can thus guide a user to the most relevant candidate product more efficiently than existing search tools.

Abstract: An application configured to be dynamically and/or incrementally updated to tailor capabilities of the application to areas of interest of a user is disclosed. The application receives one or more task-specific modules for enhancing a task-specific capability of the application. The one or more task-specific modules are identified from among a plurality of task-specific modules, based on user data indicative of interaction of the user with an electronic marketplace. The one or more task-specific modules are used to update a general module configured to implement the task-specific capability of the application to create a customized application. The customized application is used to perform a task-specific operation based on an input provided by the user, and a result of the task-specific operation to be presented to the user.

Abstract: Technologies are disclosed herein for cross-correlating metrics for anomaly root cause detection. Primary and secondary metrics associated with an anomaly are cross-correlated by first using the derivative of an interpolant of data points of the primary metric to identify a time window for analysis. Impact scores for the secondary metrics can be then be generated by computing the standard deviation of a derivative of data points of the secondary metrics during the identified time window. The impact scores can be utilized to collect data relating to the secondary metrics most likely to have caused the anomaly. Remedial action can then be taken based upon the collected data in order to address the root cause of the anomaly.

Abstract: A rack mountable bracket is described. The bracket is mountable to a rack configured for mounting equipment. The rack is also configured according to a rack standard (e.g., EIA-310) that specifies how rails of the rack are disposed, one rail to another, and how a strip of holes disposed along a length of each rail is spaced, one hole to another. In one or more implementations, the bracket includes a pair of mounting edges for mounting the bracket to a mounting pair of the rails using hole strips of the mounting pair of rails. The bracket also includes an equipment mounting rail having a hole strip disposed along a length of the rail with holes spaced according to the rack standard. The equipment mounting rail is disposed between the mounting edges, such that when the bracket is mounted to the mounting pair of rails the bracket is horizontally oriented.

Abstract: Technologies are shown for HGM based control for smart contract execution. HGM control rules control function calls at a system level utilizing function boundary detection instrumentation in a kernel that executes smart contracts. The detection instrumentation generates a call stack that represents a chain of function calls in the kernel for a smart contract. The HGM control rules are applied to HGMs collected from the call stack to allow or prohibit specific HGMs observed in functions or function call chains. HGM control rules can use dynamic state data in the function call chain. If the dynamic state data observed in function call chains does not meet the requirements defined in the HGM control rules, then the function call can be blocked from executing or completing execution. The HGM control rules can be generated by executing known sets of acceptable or vulnerable smart contracts and collecting the resulting HGMs.

Abstract: A system for transmitting information related to a network-based marketplace includes identifying information that may be interesting, useful, and entertaining to the users and to the potential users of the network-based marketplace. The identified information may be other than information that is already being displayed in listings by the network-based marketplace. The identified information may be about the sellers, the buyers or other items related to the items offered for sale.

Abstract: A system and method for standardizing user interface elements are presented. A first application is identified having a higher use metric than a second application, the first application including one or more user interface elements that have one or more respective parameters. The second application has one or more user interface elements that are similar to the user interface elements of the first application and has one or more respective parameters that are different than the respective parameters of the user interface elements of the first application. A determination of similarity is made between the user interface elements applications based upon at least one predetermined criterion. Based on the determination, one or more parameters of the user interface elements of the second application are modified to match one or more parameters of the first application.

Abstract: A user may use a client device to create a draft document by interacting with a server. The user provides an image in a message (e.g., a multimedia messaging service (MMS) message) from a different device. The server receives the image and modifies the draft (e.g., by updating a web page being displayed on the client device). This process allows the user to type text for a draft using a client device that includes a keyboard (e.g., a desktop or laptop computer) and to add an image to the draft using a second device that includes a camera (e.g., a mobile phone or tablet computer) without having to transfer the image from the second device to the first device.

Abstract: A server receives an initial query that identifies a first item listed by a first user account and an initial query value for the first item. The server provides the initial query to a first computing device associated with the first user account and receives a first response to the initial query from the first computing device. The first response indicates a rejection of the initial query value. In response to the rejection, the server identifies a second item listed by a second user account. The second item includes a shared attribute with the first item. The server substitutes the initial query with a replacement query that identifies the second item and the initial query value for the first item. The replacement query is provided to a second computing device associated with the second user account.

Abstract: One or more of the systems, apparatuses, or methods discussed herein can include a quality score for a plurality of item listings or collections of item listings. Data sparseness can be avoided, as the quality score is based on inherent properties of the listing. An item listing can be recommended to a user based on the quality score. In one or more embodiments, a method can include determining a plurality of quality scores including a quality score for each of a plurality of item listings or a plurality of collections of item listings, the quality scores determined independent of a user's attributes and independent of the user's contextual information, the contextual information corresponding to details of the user's access to a website, and recommending an item listing or collection of item listings to a user based on the quality scores and the contextual information.

Abstract: Systems and methods are provided for generating inferred reviews of service providers based on user behavior data for one or more users. The user behavior data used to generate the inferred reviews information representing a number of visits to the service provider. Additional or alternative user behavior data that may be used includes information that represents how far a user travels to a service provider, how many similar service providers the user passes on the way to the service provider, a typical time for services at the service provider, or a length of time the user has been a customer or attendees of the service provider. A service provider may include a merchant, a hotel, a physician, a contractor, another service provider that provides goods or services for a cost or may include non-profit service providers, charity-based service providers or public locations such s parks, rest stops, or other locations.

Abstract: Disclosed is technology for storing original work data on a derivative work data blockchain along with code for verifying that derivative work data is derivative of the original work data. The technology involves receiving derivative work data from a submitting entity along with proof data showing that the derivative work is derivative of the original work. If the derivative work data is verified as derivative, then the derivative work data is appended to the derivative work data blockchain.

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: Various embodiments improve search technologies and computer information retrieval by executing a query via ranking a set of search result candidates higher than another set search result candidates based at least in part on the query and determining that a first set of search result candidates are indicative of a sub-accessory to an accessory or an accessory itself.

Abstract: According to various exemplary embodiments, an electronic text message is received from a source telephone number, the electronic text message including content describing a product item. A seller of the product item is identified, based on the source telephone number, and the product item is identified, based on the content included in the electronic text message. Thereafter, a draft version of an item listing is automatically generated, where the item listing lists the product item as being for sale by the seller on a marketplace website.

Abstract: The approaches presented herein may include loading a plurality of metadata instances for a plurality of data blocks stored in a database, each metadata instance of the plurality of metadata instances indicating a respective data block structure applied to aggregate a set of data messages. The approaches may include processing a first metadata instance corresponding to a first set of one or more data blocks of the plurality of data blocks and a second metadata instance corresponding to a second set of one or more data blocks of the plurality of data blocks to perform an anomaly storage check between the first set of one or more data blocks of the plurality of data blocks and the second set of one or more data blocks of the plurality of data blocks. The approaches may include generating an output based at least in part on the anomaly storage check.

Abstract: The disclosed technologies include a robotic selling assistant that receives an item from a seller, automatically generates a posting describing the item for sale, stores the item until it is sold, and delivers or sends the item out for delivery. The item is placed in a compartment that uses one or more sensors to identify the item, retrieve supplemental information about the item, and take pictures of the item for inclusion in the posting. A seller-supplied description of the item may be verified based on the retrieved supplemental information, preventing mislabeled items from being sold.

Abstract: Embodiments for presenting real-time contact options are described herein. In example embodiments, as system identifies a number of user devices actively viewing a web page that includes a real-time contact option. The system then determines whether the number of user devices actively viewing the web page that includes the real-time contact option exceeds a predetermined limit. If the number of user devices actively viewing the web page that includes the real-time contact option exceeds the predetermined limit, the system prevents presentation, to a further user device, of the real-time contact option on the web page. Conversely, if the number of user devices actively viewing the web page that includes the real-time contact option does not exceed the predetermined limit, the system causes presentation of the web page with the real-time contact option to the further user device.

Abstract: Methods and system for text conversion are described. In one embodiment, free-form text associated with an item may be received. The item may be identified based on the free-form text. The item may be compatible with a parent item. The parent item may be identified based on the free-form text. An item descriptor may be identified in the free-form text. The item descriptor may be a particular term of the free-form text. Compatibility-based text may be constructed for the item based on identification of the parent item and the item descriptor. The compatibility-based text may be capable of being used to identify a plurality of matching items. Additional methods and systems are disclosed.

Abstract: Systems and methods are provided for receiving image data from a mobile device; identifying, based on the image data, an item and a product characteristic of the item; generating listing data of the item based on the product characteristic; determining that the item is associated with a product category; identifying a set of listings associated with the product category; applying a decay formula to the set of listings to generate a discounted number of sales and a discounted number of impressions at least one listing of the set of listings; determining a ratio of the discounted number of sales to the discounted number of impressions; determining a ranking of the set of listings based on the ratio; generating a price estimate of the item based on the ranking of the set of listings based on the ratio of the discounted number of sales to the discounted number of impressions; and causing display of a user interface including a request to list the item, the user interface including the listing data and the price e

Abstract: Method and system to facilitate transactions in a particular on-line trading platform from a third party web site may be utilized beneficially to enhance a user's experience in purchasing items referenced on third party web pages. When a user encounters, on a third party web site, a presentation of an item that is linked to a listing maintained by the on-line trading platform, the user may simply click on the presentation of the item, which causes presentation of a visual control selectable to launch a transaction processing flow facilitated by the on-line trading platform, without requiring the user to leave the third party web site.

Abstract: Apparatus and method for providing contextual recommendations based on user state are disclosed herein. In some embodiments, sensor data corresponding to at least one sensor included in an item worn by a user is received. A user state is determined based on the received sensor data. In response to a state change being satisfied by at least the user state, a recommendation is determined based on the user state and a profile associated with the user. The recommendation may be presented on an electronic mobile device associated with the user.

Abstract: A system for viewing shopping information on a social networking platform is disclosed. At the social networking platform, the system receives a request from a user device corresponding to a first user of the social networking platform to view a list of a second user of the social networking platform. The list may include items offered for transaction on a network-based commerce server. In response to receiving the request from the user device, the system forwards the request to the network-based commerce server, and then receives updated information for at least one item on the list from the network-based corner server. Then, the system communicates the updated information received from the network-based commerce server to the user device.

Abstract: Dynamic link preview generation techniques are described that overcome the challenges of conventional techniques by supporting link preview generation by a content provider system that proves the digital content via a respective network address. In one example, a content provider system, based on a request received from a service provider system, identifies a communication platform of the service provider system that is to be used to communicate the shared link. Upon identifying the communication platform, the content provider system locates customization data that describes how the link preview is to be generated for the communication platform. In response, the content provider system renders digital content available via the network address to generate the link preview.

Abstract: Various embodiments described herein utilize multiple levels of generative adversarial networks (GANs) to facilitate generation of digital images based on user-provided images. Some embodiments comprise a first generative adversarial network (GAN) and a second GAN coupled to the first GAN, where the first GAN includes an image generator and at least two discriminators, and the second GAN includes an image generator and at least one discriminator. According to some embodiments, the (first) image generator of the first GAN is trained by processing a user-provided image using the first GAN. For some embodiments, the user-provided image and the first generated image, generated by processing the user-provided image using the first GAN, are combined to produce a combined image. For some embodiments, the (second) image generator of the second GAN is trained by processing the combined image using the second GAN.

Abstract: Methods, systems, and computer programs are presented for adding new features to a network service. A method includes receiving an image depicting an object of interest. A category set is determined for the object of interest and an image signature is generated for the image. Using the category set and the image signature, the method identifies a set of publications within a publication database and assigns a rank to each publication. The method causes presentation of the ranked list of publications at a computing device from which the image was received.

Abstract: Example embodiments involve a system and methods for identifying valuable view item pages for search engine optimization. According to certain embodiments, the system performs operations that include predicting the probability of future traffic for a given product based on a number of product level factors as input variables, and identifying a selection of view item pages corresponding to the products with the probability of the highest future traffic in order to maximize the driving natural search traffic to a linked site of the corresponding view item page.

Abstract: Methods, systems, and computer storage media for processing search queries using relevance-based search refinement are provided. In response to a search query, search result items are displayed on a search interface along with selectable guidance attributes. The guidance attributes are an identified ranked set of characteristics of items based on historical user interactions of users interacting with the search result items provided in response to the search query. Upon selection of a guidance attribute, a guidance-attribute control having embedded selectable values is displayed. A selection of an embedded value is received to cause execution of an embedded-value search operation. A first embedded-value search operation is executed to identify a subset of the items using the selected value.

Abstract: Systems and methods for are provided for predicting impending failure of a database and preemptively initiating mitigating failover actions, for example by shedding connections or redirecting connection requests to an alternate database that can fulfill resources being requested. In an example embodiment, to detect a slow or unstable database, connection wait times are monitored over a rolling window of time intervals, a quantity of intervals in which at least one excessive wait time event occurred are counted during the time window, and if the quantity exceeds a threshold, the database is deemed unavailable, thereby triggering connection adjustments.

Abstract: Methods, systems, and articles of manufacture, including computer program products, are provided for image cleanup. In some embodiments, there is provide a method which may include subsampling a first image to a first level image of a multiscale transform; performing, based on a machine learning model, an identification of a foreground portion of the first level image and a background portion of the first level image; generating, based on the identification of the foreground portion and the background portion, a first mask; upscaling the first mask to a resolution corresponding to the first image depicting the foreground item; applying the upscaled first mask to the first image to form a second image depicting the foreground item; and providing the second image depicting the foreground item to a publication system. Related systems and articles of manufacture, including computer program products, are also provided.

Abstract: Systems and methods for generating feedback for a webpage based on visual interactions on the webpage are provided. In example embodiments, a user interface (UI) displaying the webpage is presented. The system receives an indication of a selection of an edit trigger and configures the webpage to receive feedback (e.g., one or more user inputs applied to webpage) from the user in response. The user inputs are received, whereby each user input is associated with an identifier of the webpage and coordinates of a location within the webpage. The system processes the user inputs including generating a feedback preview that displays each of the user inputs organized based on a corresponding feedback type. The feedback preview is displayed to the user for approval. Approval of at least a portion of the feedback on the feedback preview will cause the approved feedback to be transmitted to a corresponding entity.

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: Technologies are shown for buyer initiated automatic seller account generation where a buyer client receives an identification of a purchase item, generates an item token corresponding to the purchase item, and provides the item token to a seller client. The seller client authenticates a seller user with an authentication service, such as a biometric authentication service, receives an authentication token corresponding to the seller user, and sends an account creation request with the item token and the authentication token to an account creation service. The account creation service receives the account creation request, sends a user information request to the authentication service with the authentication token and receives seller information for the seller user from the authentication service. The account creation service creates a seller user account using the seller information, commits a purchase transaction for the purchase item, and sends an item purchase confirmation to the buyer client.

Abstract: Disclosed are systems and methods for receiving a plurality of comments at a particular phase of a transaction with a member of a networked system, classifying one or more of the plurality of comments into one of a set of predetermined sentiment classifications, applying a trained machine learning system to select a category from a set of predefined categories for each of the one or more comments, applying a natural language processing module to generate a sub-category for each of the one or more comments, associating the generated sub-categories with their respective categories for the one or more comments, and generating a display of the determined categories for the particular transaction with the generated sub-categories, each generated sub-category being graphically connected to their respective categories.

Abstract: A method for compressing data in a local cache of a web server is described. A local cache compression engine accesses values in the local cache and determines a cardinality of the values of the local cache. The local cache compression engine determines a compression rate of a compression algorithm based on the cardinality of the values of the local cache. The compression algorithm is applied to the cache based on the compression rate to generate a compressed local cache.

Abstract: In various example embodiments, a system and method for managing media bandwidth usage are disclosed. One disclosed method includes determining a network connection state of a computing device, receiving a request that requests media content, altering the request to request a synthetic representation of the media content instead of the media content in response to the network connection state being one of a set of predefined network connection states and the media content violating one or more restrictions of the network connection state, and requesting the media content in response to a user selecting the synthetic representation.

Abstract: Example methods and systems are directed to a managed inventory. A database may store information regarding items owned by a user. The information regarding an item may include a quantity owned and one or more triggering events. Based on the occurrence of a triggering event, an order for the item may be placed without user intervention. Data to the database may be provided by one or more sensors. Triggering events may be defined in terms of sensor data. The triggering event may be defined by a user or through machine learning. The order may be placed using a predetermined modality or a dynamically-determined modality based on one or more criteria, such as price, shipping speed, and the urgency of the order.

Abstract: Various embodiments use a neural network to analyze images for aspects that characterize the images, to present locations of those aspects on the images, and, additionally, to permit a user to interact with those locations on the images. For example, a user may interact with a visual cue over one of those locations to modify, refine, or filter the results of a visual search, performed on a publication corpus, that uses an input image (e.g., one captured using a mobile device) as a search query.

Abstract: Technologies are disclosed herein for distributing information. The disclosed technologies determine an application element configured to receive information that is updated at a variable rate, the information pertaining to an object. Feature data is received that is associated with the object and data associated with use of the application element. The feature data includes a time horizon for the object and supplemental information associated with the object. Based on the feature data and the data associated with use of the application element, a first rate is predicted for sending the information about the object to the application element. The information is sent to the application element at the first rate.

Abstract: A system includes one or more processors and a non-transitory machine-readable storage device comprising processor executable instructions that, when executed, cause the one or more processors to perform a set of operations comprising receiving a search request for one or more database records of a network based publication system, and identifying a first database record corresponding to at least a portion of the search request, where the database record having a first element. The set of operations also include selecting a second element of a second database record based on the first database record and adjusting the first element of the database record based on the second element. The set of operations then includes generating a formatted user interface comprising a representation of the database record and the adjusted first element, and causing, in response to the search request, presentation of the formatted user interface on the remote computing device.

Abstract: Systems and methods change a user interface for the purpose of pairing a shipping container with an item that is intended to be shipped in the shipping container. Example embodiments include a machine-implemented method for accessing a shipping request, detecting a radio signal from a candidate container using a radio receiver, detecting an impact between a pairing device and a query container using an accelerometer, determining that the query container is the candidate container, and generating a shipping record that correlates the shipping container and the item. The device can further determine that the query container is the candidate container based on the signal strength and change in signal strength of one or more signals. The device can further detect an impact between the pairing device and the query container by ranking one or more sets of acceleration data collected by the accelerometer.

Abstract: A churn prediction system includes at least one hardware processor, a memory including a historical sample set of subscriber data, and a churn prediction engine executing on the at least one hardware processor. The churn prediction engine is configured to identify the historical sample set, identify a set of attributes, automatically select a subset of attributes based on an information gain value, generate a decision tree by recursively generating nodes of the decision tree by computing an information gain value for each remaining attribute of the subset of attributes, identifying a highest attribute having the highest information gain value, and assigning the highest attribute to the node. The churn prediction engine is also configured to receive target data for a target subscriber, apply the target data to the decision tree, thereby generating a churn prediction for the target subscriber, and identify the target subscriber as a churn prediction.

Abstract: A computer server for a network-based transaction system is coupled to a kiosk via a data communications network. The kiosk includes a computer processor, an input device, an electronic display unit, a plurality of compartments, and a data communications port. The computer server receives input from a seller of an item. The input includes a listing of the item for sale on the network-based transaction system. The server identifies an available compartment from the plurality of compartments based on the size of the item for sale. The available compartment is configured to receive the item for sale from the seller. The server transmits an identification of the available compartment to the seller via the electronic display unit, and enables access to the available compartment by the seller.

Abstract: Systems, methods, and computer program products for identifying a candidate product in an electronic marketplace based on a visual comparison between candidate product image visual content and input query image visual content. Embodiments generate and store descriptive image signatures from candidate product images or selected portions of such images. A subsequently calculated visual similarity measure serves as a visual search result score for the candidate product in comparison to an input query image. Any number of images of any number of candidate products may be analyzed, such as for items available for sale in an online marketplace. Image analysis results are stored in a database and made available for subsequent automated on-demand visual comparisons to an input query image. The embodiments enable substantially real time visual based product searching of a potentially vast catalog of items.

Abstract: An experimentation platform controls testing of features by an application server. Based on a user identifier, the experimentation platform determines which feature should be provided, and the application server provides the corresponding version of a user interface. If the user behavior data shows that using a tested feature results in an improvement, the tested feature will be adopted. To determine whether or not an improvement is observed, a statistically significant amount of data is gathered. The experimentation platform gathers data regarding user behavior for the feature versions and, in response, adjusts the frequency at which each version is served. Providing the proposed version to an increased percentage of users decreases the total number of page serves required to gather statistically significant data. The experimentation platform may provide an updated projected time to completion of testing based on the changed percentage of users receiving the proposed version.

Abstract: In various example embodiments, a system and method for dynamically generating user interface elements and associated values are presented. An item listing and profile data are accessed. A set of user interface elements are dynamically generated based on the item listing and the profile data, with each user interface element configured to perform an action on the item listing. A set of values are dynamically determined, with each value being associated with a user interface element of the set of user interface elements. The set of user interface elements are then caused to be presented within the item listing.