Abstract: A recommendation system is disclosed. The recommendation system may receive a sequence of items selected by a user. Based on the sequence of items, the recommendation system may recommend one or more items. To do so, the recommendation system may apply a graph neural network. The recommendation system may receive a second sequence of items that includes the first sequence of items plus one or more items. Based on the second sequence of items, the recommendation system may recommend one or more different items by applying the graph neural network.

Abstract: Methods and systems for predicting relevant items to be presented to a user in an online environment are described. The methods and systems described herein generate models based on previous item selections to determine an overall time series model for predicting a relevant time of next item selection as well as items most likely to be selected at that time. Complementary items can be presented to the user alongside the selection of most relevant items.

Abstract: Methods and systems for generating and presenting item recommendations to a user at a retail website is disclosed. One method includes generating a set of item recommendations based on a selected item from a retail website. The method also includes identifying one or more facets in the set of item recommendations, and, for each of the one or more facets, identifying a subset of items from the set of item recommendations affiliated with the facet. The method also includes generating a user interface including the selected item and a recommendation region displaying at least some of the subset of items affiliated with the facet.

Abstract: Methods and systems for providing a digital cart management system for use by customers within a retail location. In use, a customer shops within a retail location and adds items to a digital cart as the customer is adding the items to a physical cart, e.g., at least in part by voice input. When the customer is finished shopping, the customer can checkout via a digital process, thereby bypassing point of sale devices at the retail location.

Abstract: The present disclosure provides methods and systems for providing recommendations of items to a user that are based on the user's preferences of attributes of those items. The system collects user session data and identifies attributes of items that the user may have interacted with in a previous shopping session and to assign user interest scores to the attributes based on the type user interaction with the item (e.g., selected, added to the user's shopping cart, or purchased). A decay factory may be applied to each user interest score to adjust the score over time. When a request is received for an item recommendation for the user, the system may determine user attribute preference (UAP) scores for a group of items based on the user interest scores and provide a UAP-based recommendation in a response based on the UAP scores.

Abstract: Methods and systems for providing a digital cart management system for use by customers within a retail location. In use, a customer shops within a retail location and adds items to a digital cart as the customer is adding the items to a physical cart, e.g., at least in part by voice input. When the customer is finished shopping, the customer can checkout via a digital process, thereby bypassing point of sale devices at the retail location.

Abstract: Methods and systems for generating item recommendations are disclosed. One method includes sampling from a weighted node-based graph to generate a sampled graph, wherein sampling includes selecting a plurality of nodes and, for each selected node, one or more node pairs. The selection of the node pairs is based at least in part based on a weight assigned to the node pair in the weighted node-based graph. The method further includes aggregating information from the one or more neighboring nodes into each corresponding node of the plurality of nodes in the sampled graph to generate a vector representation of the sampled graph. The method also includes applying a loss function to the vector representation of the sampled graph to generate a modified vector representation. The modified vector representation is used to generate, in response to identification of an item from an item collection, a selection of one or more recommended items from within the item collection.

Abstract: Methods and systems for generating item recommendations are disclosed. One method includes sampling from a weighted node-based graph to generate a sampled graph, wherein sampling includes selecting a plurality of nodes and, for each selected node, one or more node pairs. The selection of the node pairs is based at least in part based on a weight assigned to the node pair in the weighted node-based graph. The method further includes aggregating information from the one or more neighboring nodes into each corresponding node of the plurality of nodes in the sampled graph to generate a vector representation of the sampled graph. The method also includes applying a loss function to the vector representation of the sampled graph to generate a modified vector representation. The modified vector representation is used to generate, in response to identification of an item from an item collection, a selection of one or more recommended items from within the item collection.

Abstract: Methods and systems for authenticating and continuously re-authenticating users are disclosed. Most software applications executing on mobile devices only require a user to provide identification information (e.g., user ID and password) at the outset of launching the application, and infrequently or never subsequently request user identification information. The methods and systems described herein provide continuous protection of user identities using a combination of touch-based biometric sensor data, motion sensor data, and implicit mobile device data.

Abstract: Methods and systems for optimizing a product assortment, and managing product fulfillment, are disclosed. One method includes utilizing a model trained on item data to identify item substitution pairs within an item category of an item assortment, the item substitution pairs being identified as having a substitutability score above a predetermined threshold. The method further includes applying an assortment optimization model to generate an assortment recommendation for the item category at an identified retail location. A request for an item not included in the assortment recommendation may result in suggestion of an identified substitutable item from among the item substitution pairs.

Abstract: Methods and systems for generating and presenting item recommendations to a user at a retail website is disclosed. One method includes generating a set of item recommendations based on a selected item from a retail website. The method also includes identifying one or more facets in the set of item recommendations, and, for each of the one or more facets, identifying a subset of items from the set of item recommendations affiliated with the facet. The method also includes generating a user interface including the selected item and a recommendation region displaying at least some of the subset of items affiliated with the facet.

Abstract: Methods and systems for generating item recommendations are disclosed. One method includes sampling from a weighted node-based graph to generate a sampled graph, wherein sampling includes selecting a plurality of nodes and, for each selected node, one or more node pairs. The selection of the node pairs is based at least in part based on a weight assigned to the node pair in the weighted node-based graph. The method further includes aggregating information from the one or more neighboring nodes into each corresponding node of the plurality of nodes in the sampled graph to generate a vector representation of the sampled graph. The method also includes applying a loss function to the vector representation of the sampled graph to generate a modified vector representation. The modified vector representation is used to generate, in response to identification of an item from an item collection, a selection of one or more recommended items from within the item collection.

Abstract: Methods and systems for providing a digital cart management system for use by customers within a retail location. In use, a customer shops within a retail location and adds items to a digital cart as the customer is adding the items to a physical cart, e.g., at least in part by voice input. When the customer is finished shopping, the customer can checkout via a digital process, thereby bypassing point of sale devices at the retail location.

Abstract: Aspects of the present disclosure describe systems and methods for rapidly detecting threats or other security breaches in enterprise networks. In particular, all enterprise network communications may be monitored to detect anomalous events. In one example, each event log in a collection of event logs may be evaluated, wherein an event log having one or more features is monitored and identified as being anomalous based on identifying one or more anomalous features therein. Anomalous features are identified as being anomalous based on the existence of one or more features in the event log that deviate from characteristic contextual features. Rules or models may thereafter applied to each event log containing the anomalous feature.

Abstract: Methods and systems for predicting relevant items to be presented to a user in an online environment are described. The methods and systems described herein generate models based on previous item selections to determine an overall time series model for predicting a relevant time of next item selection as well as items most likely to be selected at that time. Complementary items can be presented to the user alongside the selection of most relevant items.

Abstract: Methods and systems for authenticating and continuously re-authenticating users are disclosed. Most software applications executing on mobile devices only require a user to provide identification information (e.g., user ID and password) at the outset of launching the application, and infrequently or never subsequently request user identification information. The methods and systems described herein provide continuous protection of user identities using a combination of touch-based biometric sensor data, motion sensor data, and implicit mobile device data.

Abstract: Aspects of the present disclosure describe systems and methods for rapidly detecting threats or other security breaches in enterprise networks. In particular, all enterprise network communications may be monitored to detect anomalous events. In one example, each event log in a collection of event logs may be evaluated, wherein an event log having one or more features is monitored and identified as being anomalous based on identifying one or more anomalous features therein. Anomalous features are identified as being anomalous based on the existence of one or more features in the event log that deviate from characteristic contextual features. Rules or models may thereafter applied to each event log containing the anomalous feature.

Abstract: Systems and techniques for user authentication are described. A portable electronic device can include an imaging sensor and a motion sensor. Multiple images of a face of a user can be acquired by using an imaging sensor. Motion information can be obtained by using a motion sensor. Next, a first motion vector can be determined based on the multiple images, and a second motion vector can be determined based on the motion information. The user can then be authenticated based on (1) determining a similarity measure between the first motion vector and the second motion vector, and (2) performing facial recognition on at least one of the multiple images. Note that the similarity measure can be used to detect a virtual-camera attack. Specifically, authentication can fail if the similarity measure is less than a threshold.

Abstract: An efficient process for enzymatic hydrolysis of fats and oils in a homogenous mixture is provided herein. The present invention in particular provides a process for production of fatty acids, sn-regio mono-acylglycerol (MAG), sn-regio di-acyl-glycerols (DAG), and glycerol from fats, wherein more than 98% fats can be converted into the desired product. The present invention also provides a process for the production of fatty acids and glycerol, virtually free of sn-regio diacyl-glycerols (DAG) and comprising less than 5% sn-regio mono-acylglycerol (MAG) in the end product.

Abstract: Systems and techniques for user authentication are described. A portable electronic device can include an imaging sensor and a motion sensor. Multiple images of a face of a user can be acquired by using an imaging sensor. Motion information can be obtained by using a motion sensor. Next, a first motion vector can be determined based on the multiple images, and a second motion vector can be determined based on the motion information. The user can then be authenticated based on (1) determining a similarity measure between the first motion vector and the second motion vector, and (2) performing facial recognition on at least one of the multiple images. Note that the similarity measure can be used to detect a virtual-camera attack. Specifically, authentication can fail if the similarity measure is less than a threshold.