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 dynamically generating virtual marketplace platforms are presented. The system receives a set of facility data, a set of selections for a set of user interaction objects, and a set of object placement selections. The set of user interaction objects includes a first subset and a second subset. The system generates a virtual facility comprising the facility data and the set of user interaction objects distributed based on the object placement selections. The system receives user data for a user interacting with the virtual facility and one or more objects of the first and second subset of user interaction objects, dynamically arranges the second subset of user interaction objects into a second arrangement, and causes presentation of the virtual facility and the set of user interaction objects to the user.

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: Systems and methods for improving a search process are provided. A networked system accesses, from online sources, fashion trend information including pictures illustrating fashion trends. The networked system determines a plurality of top fashion trends, and extracts, using an image detection algorithm, images of fashion items from a picture associated with each of the top fashion trends. Using the extracted images, the networked system performs an image search for matching inventory items. The networked system then generates and stored a plurality of fashion trend user interfaces, whereby the plurality of fashion trend user interfaces each comprise selectable elements that represent the plurality of top fashion trends. At runtime, the networked system receives an indication to initiate a search for fashion by trends, and in response, accesses the plurality of stored fashion trend user interfaces. One of the plurality of stored fashion trend user interfaces is presented on a user device.

Abstract: A distributed search system can be partitioned into buckets based on entities and time periods. Addresses for the partitions can be formed from entity parameters and time period parameters. An indexing scheme for the partitions can be maintained at one or more search clusters, which may be geographically separate from one another. Consistency can be maintained across the search clusters though routing queries between clusters based at least in part on the status of partitions.

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: To improve the user experience, browse nodes for popular combinations of categories and aspects are desirable. When a particular combination of category and aspects is found to have been requested at a frequency that exceeds a threshold, the existence of a browse node for that combination is checked and, if the browse node is missing, a request to create the browse node is generated. In some example embodiments, an entire set of missing browse nodes is generated based on recognition of a pattern of category and aspect combinations being requested.

Abstract: The disclosed technologies identify opportunities to display relevant three-dimensional (“3D”) model data within a real-world environment as a user wears a wearable device. The 3D model data can be associated with objects, or items, and the 3D model data rendered for display is relevant in the sense that the items are determined to be of interest to the user and the items fits within the real-world environment in which the user is currently located. For instance, the techniques described herein can recognize items typically found in a kitchen or a dining room of a user's house, an office space at the user's place of work, etc. The characteristics of the recognized items can be identified and subsequently analyzed together to determine preferred characteristics of a user. In this way, the disclosed technologies can retrieve and display an item that correlates to (e.g., matches) the preferred characteristics of the user.

Abstract: Described are computing systems and methods configured to detect a small, but meaningful, anomaly within one or more metrics associated with a platform. The system displays visuals of the metrics so that a user monitoring the platform can effectively notice a problem associated with the anomaly and take appropriate action to remediate the problem. An operational visual includes a radar-based visual with a heatmap arranging metrics, and a node representing a state of the metrics. Moreover, the system uses an ensemble of unsupervised machine learning algorithms for multi-dimensional clustering of hundreds of thousands of monitored metrics. Via the visuals and the implementation of the machine learning algorithms, the described techniques provide an improved way of representing and simulating many metrics being monitored for a platform. Moreover, the techniques are configured to expose actionable and useful information associated with the platform in a manner that can be effectively interpreted.

Abstract: Techniques for removing purchases from online containers are described. For example, an indication of a purchase of a first product at a first store by a user is received. A user account associated with the user is identified. The user account has an online container for storing one or more desired products. The first product is matched to one or more desired products based on one or more product characteristics of the first product and of the one or more desired products. The one or more desired products that match the first product are removed from the online container.

Abstract: Techniques for modifying a garment based on gestures are presented herein. An access module can access a first set of sensor data from a first sensor, and a second set of sensor data from a second sensor. A garment simulation module can generate a three-dimensional (3D) garment model of a garment available for sale draped on an avatar based on the first set of sensor data and the second set of sensor data. A display module can cause a presentation, on a display of a device, of the 3D garment model draped on the avatar. Additionally, the garment simulation module can determine a modification gesture associated with the 3D garment model draped on the avatar based on the first set of sensor data and the second set of sensor data. Furthermore, the garment simulation module can modify the 3D garment model based on the determined modification gesture.

Abstract: Methods, systems, and computer program products for providing transaction verification through enhanced authentication are provided. A method performed by a computer system may include receiving an application programming interface (API) request from a client, detecting a change associated with the API request as compared to a prior use of the API by the client, generating an encrypted challenge to authenticate the API request based on detecting the change, and issuing the encrypted challenge to the client to authenticate the API request.

Abstract: A method for defining, generating, and using a global back-end taxonomy is disclosed. It is identified that a listing of an item is exposed to a plurality of users of a first subsystem via a set of categories of a first front-end taxonomy. The listing of the item is mapped to a set of categories of a global back-end taxonomy, the global back-end taxonomy being maintained independently of the first front-end taxonomy and a second front-end taxonomy, the second front-end taxonomy being associated with a second subsystem. A category of the set of categories of the global back-end taxonomy is mapped to a category of a set of categories of the second front-end taxonomy associated with the second subsystem. The listing of the item is exposed to a plurality of users of the second subsystem via the set of categories of the second front-end taxonomy.

Abstract: Systems and methods of site traffic control are disclosed. In some example embodiments, a request for an online service to perform an operation is received from a user on a client device, and at least one overload condition for the online service is detected, or otherwise determined, with the overload condition(s) corresponding to a request time of the request. A standard of restriction is selected from a plurality of standards of restriction based on the overload condition(s), and the selected standard of restriction is used as a basis for either denying or permitting the user access to the operation of the online service.

Abstract: A method and system are described to provide a user-widget-based transaction environment. In one example embodiment, an electronic magazine may be presented to a user device as a widget without using a browser. The electronic magazine may comprise two or more data pages. A user selection of at least one of the two or more data pages may be detected and then communicated from the user device across a network for further processing.

Abstract: A system according to an embodiment comprises one or more processors; and one or more memories in communication with the one or more processors and adapted to store a plurality of machine-readable instructions which when executed by the one or more processors are adapted to cause the system to: offer, by a merchant at a Point of Sale (POS), at least one payment option in connection with a transaction for at least one item, wherein the payment option(s) is presented in a display tailored to a specific user based on information maintained by the merchant about the specific user; and process the transaction using a payment option selected by the user.

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 text content and input query image visual text content. Unlike conventional optical character recognition (OCR) based systems, embodiments automatically localize and isolate portions of a candidate product image and an input query image that each contain visual text content, and calculate a visual similarity measure between the respective portions. A trained neural network may be re-trained to more effectively find visual text content by using the localized and isolated visual text content portions as additional ground truths. The visual similarity measure serves as a visual search result score for the candidate product. Any number of images of any number of candidate products may be compared to an input query image to enable text-in-image based product searching without resorting to conventional OCR techniques.

Abstract: In an example embodiment, a distributed storage system includes a service tier including a service node to receive a request for a logical object comprising binary data and metadata describing the binary data, and a storage tier including a plurality of storage nodes, wherein one or more of the storage nodes is to store the metadata describing the binary data. The distributed storage system also includes a coordination tier to store mapping information identifying the one or more of the storage nodes storing the metadata. The service node is also to receive the mapping information from the coordination tier, to access the metadata describing the binary data from one of the one or more of the storage nodes based on the mapping information, and to return the metadata describing the binary data in a response to the request.

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: Techniques for lip-reading session triggering events are described. A computing device is equipped with lip-reading capability that enables the device to “read the lips” (i.e., facial features) of a user. The computing device determines when a triggering event occurs to automatically cause the computing device to switch from one input type to a lip-reading session. Lip-reading is also used in conjunction with other types of inputs to improve accuracy of the input. Machine learning is used to personalize the lip-reading capability of the computing device for a particular user.

Abstract: Methods, systems, and media for improving computer security and performance of security are disclosed. In one example, a computer security system comprises a key management monitor, and two key elements comprising a first key element and a second key element. The first key element is stored at a first location address within a computer memory and the second key element is stored at a second location address. The key management monitor is configured to determine or receive a time duration for performing a data dump of contents of the computer memory. In one example, the key management monitor is further configured to control a location of the first key element within the computer memory, wherein the location address of the first key element is changed within a time period that is less than the time duration for performing the data dump of contents of the computer memory.

Abstract: In various example embodiments, systems and methods to provide proximity recommendations are provided. In example embodiments, data representing prioritized recommendations for a user is received. The data representing the prioritized recommendations is used to generated a composite visual representation by embedding select prioritized recommendations into a visual representation. The composite visual representation presents a higher prioritized recommendation in a more spatially prominent manner than a lower prioritized recommendation. The composite visual representation is then presented to the user.

Abstract: There are provided systems and methods for synchronized media capturing for an interactive scene. A user at a venue may watch an event unfold at the venue. The venue may include wireless beacons established throughout the venue. The wireless beacons may be configured to establish short range wireless communications with the user's device. Once a connection is established, the wireless beacons may instruct the user's device to capture media of an instance during the event. The wireless beacons may similar instruct other user's devices to capture media of the instance at the same time, thereby synchronizing media capturing of a particular instance during the event. The user may review the media and select to delete the media or upload the media to a media sharing service. The server may further process the media into an interactive scene.

Abstract: A computer-implemented system and method for providing information tagging in a networked system is disclosed. The apparatus in an example embodiment includes a tag engine configured to process a database of categorized product listings; to receive a user-provided tag associated with at least one of the product listings; to retain the user-provided tag; and to serve the user-provided tag to a user viewing at least one of the product listings.

Abstract: Systems and methods of rate limiting are disclosed herein. In some example embodiments, a rate limiter service receives a request from an online application to access an online resource, and the rate limiter service transmits an indication of the request to a back end system, and an enforcement decision corresponding to the online resource is received from the back end system, with the enforcement decision comprising an instruction to either permit or deny access to the online resource, and the receiving of the enforcement decision from the back end system being performed asynchronously with the receiving of the request and the transmitting of the indication. In some example embodiments, the enforcement decision received from the back end system is stored, the stored enforcement decision is accessed in response to the receiving of the request, and the request is responded to using the accessed enforcement decision.

Abstract: This disclosure provides systems and methods of determining price quantiles for associated search queries and displaying said price quantiles when one or more search queries are received. In various embodiments, a search query for an item offered for sale may be received. Search results from a plurality of offered items may be determined based on the search query. The search results may each be associated with a price. The search results may be displayed, and a selection of a search result may be received. The price of the selected search result may be associated with the received search query. Various price quantiles may be determined based on the associated price(s). In addition, the price quantiles may each include prices associated with the search results. The determined price quantiles may then be displayed in response to a second search query determined to be related to the first search query.

Abstract: Methods and systems to automatically respond to a request for product information are described. In one embodiment, a data collection module may collect product data over a network, identify that the product data is related to a particular product, and store the product data and an association between the product data and the particular product in a database. An instant messaging engine may receive a request for the product data after the product data is stored in the database and an interpreter module may identify, in response to the request, the request to correspond to the particular product and retrieve the product data based on the association between the particular product and the product data. The instant messaging engine may also transmit, using an instant messaging protocol, a response to the request, the response including the product data.

Abstract: In accordance with one or more embodiments of the present disclosure, a method for leveraging a social network to search for local inventory includes communicating with a first mobile communication device over a network, the first mobile communication device associated with a user, and communicating with a second mobile communication device over the network, the second mobile communication device associated with a social network contact. The method further includes obtaining a geo-location of the second mobile communication device, processing a search request from the first mobile communication device, obtaining a radius of coverage for a merchant, determining whether the geo-location of the second mobile communication device is within the radius of coverage of the merchant, and providing a listing to the first mobile communication device of one or more items for sale by the merchant when the second mobile communication device is within the radius of coverage of the merchant.

Abstract: Technologies are shown for trust delegation that involve receiving a first request from a subject client and responding by sending a first token having first permissions to the subject client. A second request from a first actor includes the first token and responding involves linking the first actor to the subject client in a trust stack and sending a second token to the first actor with second permissions, the second token being a first complex token that identifies the subject client and the first actor. A third request from a second actor includes the second token and responding to the third request involves linking the second actor to the first actor in the trust stack, and sending a third token to the second actor partner with third permissions, the third token being a second complex token that identifies the first actor and the second actor.

Abstract: Methods, systems, and media for user authentication in hybrid online and real-world environments are disclosed. In one example, a method comprises providing a real-world environment including a display of physically retrievable items available for purchase, detecting the presence of a user device associated with a user in the real-world environment, and storing identity data received from the user device. Interest data for one of the physically retrievable items is identified based on sensed biometric data of the user and an online offering for a comparable online item is automatically implemented without manual operation of the user device. A user identification associated with an online account is derived based on the stored identity data received from the user device and the online offering for the item comparable to the physically retrievable item is provided to the online account associated with the user identification.

Abstract: Techniques for mapping size information associated with a client to target brands, garments, sizes, shapes, and styles for which there is no standardized correlation. The size information associated with a client may be generated by modeling client garments, accessing computer aided drawing (CAD) files associated with client garments, or by analyzing a history of garment purchases associated with the client. Information for target garments may be generated in a similar fashion. A system may then create a standardized scale with a set of sizes for a target, and map a client base size to that standardized size scale. Similar matching and mapping may also be done with shape and style considerations. A recommendation based on the mapping may then be communicated to the client.

Abstract: In a system and method of recognizing a barcode from a stream of video frames, a processor-implemented camera module receives a stream of video frames, with at least one video frame including a barcode. A processor-implemented barcode blur estimate module estimates an amount of defocus blur in a video frame. The processor-implemented barcode blur estimate module further estimates an identity of the barcode. A processor-implemented barcode localization module identifies a region of the video frame containing the barcode. A processor-implemented barcode geometric modeler module generates a geometric model of the barcode that includes an identified barcode deformity. A processor-implemented barcode decoder module decodes the barcode from the video frame using the estimated amount of defocus blur, the estimated identity of the barcode, and the geometric model of the barcode.

Abstract: Systems and methods to provide a navigated-shopping service are discussed. In an example, a method for navigated-shopping can include receiving a destination location, accessing a route to the destination, displaying the route with indications of a plurality of items for purchase, receiving selection of a selected item, and purchasing the selected item. The plurality of items for purchase can be within a predefined distance of at least one point along the route. The selection of the selected item can include selection of a retail location of a plurality of retail locations along the route.

Abstract: A method of projecting a likeness of an item onto a surface is disclosed. A determination that a user is interested in an item is made. A schematic corresponding to the item is identified based on information about the item. The user is provided with an option to project a likeness of the item onto a surface. Based on an accepting of the option by the user, a device of the user is instructed to project the likeness of the item onto the surface based on the schematic.

Abstract: The “free world replication protocol” makes use of client computing resources, wherein the clients are not part of the replicated key-value store, but instead reside in the “free world” outside of the dedicated resources of the nodes of the replicated key-value store. In the free world replication protocol, only a single “write” client is authorized to modify the key-value store at any time but any number of clients may be authorized to read data from the key-value store. The write client sends its transactions to multiple nodes in the replicated key-value store. As a result, the latency between the transaction being sent from the client and the transaction being received by the multiple nodes is reduced by comparison to existing protocols in which each client sends transactions to a single node and that node forwards the transactions. A consensus protocol, driven by a master node, is used to periodically ensure consistency, but the data transactions themselves do not make use of a master node.

Abstract: Technologies described reduce the amount of time between requesting content and receiving the requested content. In some embodiments, a client provides a search query. A search result page is generated and, prior to returning the search result page to the client, some or all of the search results are asynchronously pre-fetched and cached. The search query can include custom parameters that are also included in the pre-fetch requests. Web addresses in the search results page can be modified to indicate whether a prefetch operation was initiated. Once a user activates one of the search results, the responding web server uses the cached data while generating a response.

Abstract: Systems and methods for preemptive adjustments of connections in a server connection pool are provided. In example embodiments, a number of quality of service engines analyze server connection pool metrics data to generate instructions to increase or decrease the number of connections in a connection pool, preemptively, before shortages or surpluses of connections occur. Corrective engines can analyze performance of the quality of service engines and can, when necessary, instruct the quality of service engines to modify their prediction mechanisms.

Abstract: Techniques and systems are described that leverage computer vision as part of search to expand functionality of a computing device available to a user and increase operational computational efficiency as well as efficiency in user interaction. In a first example, user interaction with items of digital content is monitored. Computer vision techniques are used to identify digital images in the digital content, objects within the digital images, and characteristics of those objects. This information is used to assign a user to a user segment of a user population which is then used to control output of subsequent digital content to the user, e.g., recommendations, digital marketing content, and so forth.

Abstract: A method may include obtaining a weight of merchandise supported by a shelf and obtaining identifier data of the merchandise supported by the shelf. The identifier data may be wirelessly received from tags associated with the merchandise. The method may also include determining information for presentation to a consumer regarding the merchandise based on the weight of the merchandise and the identifier data of the merchandise. The method may also include providing the information for presentation to the consumer of the merchandise when the consumer is proximate the merchandise that is supported by the shelf.

Abstract: A system comprises servers having processing circuits and a non-transitory storage medium, the non-transitory storage medium having computer code that is executable to cause the system to receive a unique identifier and to identify, in response to receiving the unique identifier, a virtual object stored by the one or more servers in association with the unique identifier. The computer code is further executable to transmit the virtual object and an immersive simulated three-dimensional environment to a separate device and to receive virtual motion data of a virtual movement of the virtual object relative to the immersive simulated three-dimensional environment. The computer code is further executable to determine that separate device is authorized to access a resource of the system and to transmit, in response to the determination that the user of the separate device is authorized, an authorization message to the separate device.

Abstract: Disclosed is a security authentication system for a membership login of an online website capable of ensuring a safe membership login without having to directly entering a membership ID and a password for a membership login of a certain online website on a user terminal being used in association with a smartphone for a private or public purpose, and a method thereof.

Abstract: Systems and methods for time-decay analysis of a photo collection for automated item listing generation are described. A system stores image data in non-transitory memory of a computing device. The system identifies a first item represented in the image data as a first image and a date associated with the first item. The system determines the first item satisfies a date threshold based on the first date. Finally, the system generates a request including information for publishing a first listing of the item in a network-based publication system.

Abstract: Systems and methods for weak authentication data reinforcement are described. In some embodiments, a request to authenticate a user is received. A user password is determined to be a weak password. The user is verified to be human by initiating a human verification process. In response to verifying that the user is human, an option is provided to replace the weak password with a strong password.

Abstract: Methods and systems for generating new product images are disclosed. In one aspect, a method includes identifying, via hardware processing circuitry, a template for a category of products, the template defining locations of attributes of products belonging to the category, identifying, via the hardware processing circuitry, common attributes of products of the category based on the template, averaging, via the hardware processing circuitry, corresponding pixel values across images representing the products having the common attributes, generating, via the hardware processing circuitry, a new product image representing a new product based on the averaged pixel values; and generating, via the hardware processing circuitry, a modified new product image by varying attributes of the new product based on the locations of the attributes defined by the template.

Abstract: Systems and methods for navigation control for mobile devices are provided. In example embodiments, a navigation system causes presentation of a navigation icon at a user interface. Navigation between a plurality of pages at the user interface is initiated with a single tap and hold action. In response to a drag motion, following the single tap and hold action without releasing the hold action, information display at the user interface is adjusted, thereby enabling navigating between multiple information content with a single tap, hold, and drag action of the user.

Abstract: Methods and systems are provided for social shopping on a network-based marketplace. The system receives a selection, over a network, at a social shopping platform. The selection identifies a request from a user in a first community of users and is associated with a listing describing an item for sale. The social shopping platform includes multiple network-based marketplaces respectively associated with communities. The communities include the first community of users being associated with a first network-based marketplace. The system identifies the first network-based marketplace based on the request. The first network-based marketplace is used by the first community of users for transacting items of a single domain. Finally, the system updates a user reputation score based on the activity associated with the first network-based marketplace and presents second user interface information, over the network, including the listing.

Abstract: A machine may be configured to provide an online pluggable three-dimensional platform for publication of three-dimensional representations of items. For example, the machine generates a first software unit that corresponds to the three-dimensional representation of the item, and a second software unit that corresponds to an online three-dimensional platform that is pluggable to include the three-dimensional representation of the item corresponding to the first software unit. The online three-dimensional platform includes one or more pluggable slots for receiving one or more three-dimensional representations of one or more items. The machine generates an enhanced user interface on the client device based on causing an execution of the first software unit and the second software unit. The causing of the execution results in a display, in the enhanced user interface of the client device, of the three-dimensional representation of the item plugged into a pluggable slot of the online three-dimensional platform.

Abstract: Techniques are described herein that overcome the limitations of conventional techniques by bridging a gap between user interaction with digital content using a computing device and a user's physical environment through use of augmented reality content. In one example, user interaction with augmented reality digital content as part of a live stream of digital images of a user's environment is used to specify a size of an area that is used to filter search results to find a “best fit”. In another example, a geometric shape is used to represent a size and shape of an object included in a digital image (e.g., a two-dimensional digital image). The geometric shape is displayed as augmented reality digital content as part of a live stream of digital images to “assess fit” of the object in the user's physical environment.

Abstract: In a networked data system, a discovery protocol enables clients to establish connections to one a plurality of database servers to utilize a distributed connection service. The service manages connections between application servers, i.e. clients, and databases. An initial request from the client is received by a load balancer. The load balancer responds to the client by identifying an assigned connection to one of the database servers based on load considerations. The client sends a secondary request directly to the assigned connection, bypassing the load balancer. The service establishes a persistent link on the assigned connection and assigns a time-to-live (TTL), during which the service connects data requests to the databases. Upon expiration of the TTL, the service completes a next data request received, then notifies the client that the connection is no longer valid, thereby requiring a new connection through the load balancer and rebalancing system traffic.

Abstract: In accordance with embodiments of the present disclosure, systems and methods for facilitating electronic commerce over a network include communicating with a plurality of users via a plurality of user devices over the network, receiving a login request from a first user via a first user device over the network, accessing an account related to the user based on information passed with the login request, receiving a snaplist file related to a multiple image listing provided by the first user via the first user device, processing the snaplist file by extracting the multiple image listing from the snaplist file, and displaying the multiple image listing to one or more other users via one or more other user devices.