Abstract: Aspects of the present disclosure provide techniques that utilize artificial intelligence (AI) to preemptively identify and prioritize risks for retailers from shrink loss. Specifically, features of the present disclosure provide actionable prescriptions to prevent shrink based on the output of a hybrid machine learning (ML) system that accurately identifies shrink risk factors and implements a cost-effective shrinkage control plan to reduce the retail theft. The shrinkage control plan may then be displayed to the user on a display device (or user interface) in order to allow for the user (e.g., store manager) to implement the recommendations developed by the recommendation engine.

Abstract: A method of generating a plurality of behavioral site lists. The method comprises receiving a plurality of interest category lists by a behavioral site list generation application executing on a computer system, wherein each interest category list comprises a plurality of pseudonymous subscriber identities associated with the pre-defined interest category; receiving a plurality of data on subscriber visits to web sites and on application identities by the application; generating behavioral site lists by the application based on determining over-indexing of pseudonymous subscriber identities provided in the data on subscriber visits to web sites and on application identities in the interest category lists, wherein each behavioral site list comprises a plurality of web site addresses and a plurality of application identities that are deemed to have an above average association to subscribers with an interest in the interest category associated with the behavioral site list.

Abstract: An inventory prediction system is described that outputs a predicted inventory item not included in a user's known inventory using a cross-category directional graph that represents item categories as nodes. The inventory prediction system implements a prediction model trained using machine learning to output the predicted inventory item using the graph and at least one item from the user's known inventory. The inventory prediction system is further configured to generate a listing recommendation for the predicted inventory item. To do so, the inventory prediction system implements a logistic regression model trained using machine learning to calculate a probability that the listing recommendation should be generated using attributes of the predicted inventory item and attributes of currently trending items.

Abstract: A method for predicting a price of any subtractively manufactured part utilizing artificial intelligence at a computing device. The method comprises receiving a manufacturing request datum, wherein the manufacturing request datum further comprises at least an element of user mechanical part data, selecting a correlated dataset containing a plurality of data entries. The method further comprises generating, at a clustering unsupervised machine-learning model, at least a first correlated compatible part element, receiving, at a supervised machine-learning model, a first training set, generating, at a supervised machine-learning model as a function of the first training set, an external price output, and determining a price ratio output, wherein determining the price ratio output further comprises generating a loss function of a part specific variable and minimizing the loss function.

Abstract: A crowd management system includes at least one local controller associated with an attraction area of an individual attraction within a theme park. The crowd management system includes a transceiver of the at least one local controller, where the transceiver receives guests data via wireless signals from guest-associated devices within a detection range of the local controller. The crowd management system includes a remote central controller in communication with the at least one local controller and the guest-associated device. The remote central controller receives the guest data from the at least one local controller and determines one or more crowd metrics of the individual attraction based on the guest data. The remote central controller generates an activity command based on the one or more crowd metrics. The remote central controller transmits the activity command to at least one guest-associated device of the guest-associated devices.

Abstract: Methods, apparatus, and processor-readable storage media for automatically determining enterprise-related action sequences using artificial intelligence techniques are provided herein. An example computer-implemented method includes identifying at least one enterprise-related prospect by processing data pertaining to one or more entities; classifying the at least one enterprise-related prospect, based at least in part on estimated prospect conversion time, by using at least a first set of one or more artificial intelligence techniques; determining at least one prospect conversion action sequence for the at least one enterprise-related prospect, based at least in part on the classifying of the at least one enterprise-related prospect, by using at least a second set of one or more artificial intelligence techniques; and performing one or more automated actions based at least in part on the at least one prospect conversion action sequence.

Abstract: A system, computer program product, and method are presented for forecasting a spatio-temporal calendar including predicted regions of interest based on time dependent factors such as long-term weather predictions, time-independent factors, and travel constraints. The method includes collecting information and constraints with respect to service visits. At least a portion of the collected information and constraints are directed toward weather and climate. The method also includes predicting weather and climate impacts on at least one geographical region of interest. The method further includes predicting, subject to the predictions of weather and climate impacts, one or more locations of interest within the at least one geographical region of interest that would be impacted by one or more service visits. The method also includes generating one or more spatio-temporal calendars that include the one or more locations of interest scheduled for the one or more service visits.

Abstract: In some implementations, a system may receive, from an analysis system, a data stream associated with monitoring an environment. The system may process, using a first model, the data stream to detect an object associated with a service provided by an application. The system may analyze a monitoring configuration of the analysis system. The system may determine, based on processing the data stream, service data associated with providing the service in association with the object. The system may configure, based on the monitoring configuration, an edge device to access the data stream and host a second model to process the service data according to the data stream. The system may receive, from the edge device, a service output associated with providing the service in association with the object. The system may perform an action associated with the service output and the object.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support automated optimization of product management systems. In embodiments, automated optimization of component tools of the product management system is provided by automated evaluation and optimization of associated rules and metadata. In embodiments, metadata and rules may be associated to each other by an assessment engine. A recommendation engine may then identify non-compliant metadata, may determine a condition of the rule, and/or may generate recommendations for the rules based on the non-compliant metadata. Automated optimization of the product management system may include automated creation and mapping of decomposition relationships between commercial products and technical products. In embodiments, input data may be parsed into a set of object with unique attribute fields, which may then be validated.

Abstract: A hybrid dimming controller for a lighting control system providing isolated class 1 and class 2 dimming outputs. The controller has two NEC class 1 outputs for providing independent low-voltage dimming-control signals for two lighting loads and two NEC class 2 outputs for providing the same two independent dimming control-signals for the lighting loads. Thus, the controller has both a class 1 and a class 2 outputs for delivering the same dimming-control signal for each of the two lighting loads while maintaining within the controller the isolation that is required between class 1 and class 2 circuits.

Abstract: In some implementations, a system is configured to selectively distribute programs to remote devices based on monitoring performed by the remote devices. The system includes a server system that can distribute configuration data for the respective programs to remote devices over a communication network and monitor incoming data received from the remote devices over the communication network. The system can collect, from the respective remote devices, monitoring data that is generated for the programs by the remote devices and is provided over the communication network. The system can adapt a scoring process for prioritizing the plurality of programs for different remote devices based on the collected monitoring data. The system can distribute, to each of one or more of the remote devices, configuration data corresponding to one or more programs identified for the one or more remote devices using the adapted scoring process.

Abstract: A central database system trains a machine-learned model based on training data identifying entity characteristics of account holder entities, content item characteristics of a content item presented to the account holder entities, and interactions between the account holder entities and the presented content item. The central database system then identifies a target set of account holder entities, and applies the trained machine-learned model to the entity characteristics of each account holder entity of the target set of account holder entities, the entity characteristics of each of the account holder entities that previously interacted with the content item, and the content item characteristics of the content item to identify a subset of the target set of account holder entities for presentation of the content item. The content item is then displayed to the subset, the content item includes an interface element that, when selected, causes an interaction to take place.

Abstract: Systems and methods for executing queries on a bitmap index are disclosed. The system may receive a first data stream from a database and generate a bitmap index based on the first data stream. The system may receive an input selection of one or more data conditions from a user device and generate a Boolean expression based on the input selection. The system may query the bitmap index using the Boolean expression and generate a bitmap vector. The system may output a first data subset represented by the generated bitmap vector to a graphical user interface. The bitmap index may include probabilistic entries, and the system may validate the probabilistic entries by receiving a second data stream, identifying one or more entries correlated to the probabilistic entries, determining a divergence between the identified entries and the probabilistic entries, and updating parameters of a classifier model associated with the probabilistic entries.

Abstract: A system comprising: a skills data store; an employee action data store; at least one hardware processor; and one or more software modules that are configured to, when executed by the at least one hardware processor, retrieve skills data and employee action data from the skills data store and employee action data store, train a classification model, wherein training a classification model comprises performing feature preprocessing, generating an LDA topic vector and TF/IDF Word2Vec similarity scoring, and use AutoML to train ML models, and infer employee skills and levels based on the classification model and employee action data.

Abstract: Systems and computer-implemented methods are described for modeling card inactivity. For example, hierarchical modeling may be used in which a first level classifier may be trained and validated to predict whether a card will be inactive. For cards predicted to become inactive by the first level classifier, a second level classifier may be trained and validated to predict when the card will become inactive. The first level classifier may include a binary classifier that generates two probabilities that respectively predict that the card will and will not become inactive. The second level classifier may include a multi-class classifier that generates a first probability that the card will become inactive at a first time period (such as one or more months in the future) and a second probability that the card will become inactive at a second time period. The multi-class classifier may generate other probabilities corresponding to other time periods.

Abstract: Embodiments of systems and methods for resolving remote meeting conflicts using learned attributes and context information are described. In some embodiments, an Information Handling System (IHS) may include a processor and a memory coupled to the processor, the memory having program instructions stored thereon that, upon execution by the processor, cause the IHS to: determine, based upon context information collected by the IHS, that a user of the IHS is more likely to attend a first remote meeting than a second remote meeting, where the first and second remote meetings are scheduled to take place, at least in part, concurrently; and in response to the determination, apply one or more settings to the IHS that are associated with the first remote meeting.

Abstract: Certain aspects of the present disclosure provide techniques for training and using predictive models to predict the occurrence of an event within a software application. An example method generally generating a spatially sampled data set for a set of users of a software application. The spatially sampled data set includes, for each respective user of the set of users, an amount of time the user has spent, a number of discrete portions of the software application the user has visited, and an indication of whether the user has completed a defined task. A spatio-temporally sampled data set for users in the spatially sampled data set is generated, including, for each respective user in the spatially sampled data set, a plurality of candidate timestamps. A predictive model is trained based on the spatio-temporally sampled data set.

Abstract: Systems and methods associated with providing content personalization are disclosed. In one embodiment, an exemplary method may comprise receiving first data including content preferences associated with an audience, receiving second data including an initial digital message being proposed for transmission to the audience, generating a recommendation data set based at least in part on the first data and the second data, wherein the recommendation data set identifies at least one recommended content type and at least one recommended message type, determining via a natural language generation machine learning model suggested content for the audience, and providing the suggested content for dissemination to the audience.

Abstract: Methods and systems are described herein for receiving a document (e.g., a technical paper), identifying sections of the document, and inputting each section into a corresponding machine learning model that has been trained using previously reviewed documents to process text and other data within a specific section. The machine learning model may output a score indicating the degree of compliance to a particular standard of a particular document. In addition, various recommendations for content to be added to the document may be identified and provided to the user along with the score for each section.

Abstract: The disclosure includes systems and methods for determining a change window for taking an application off-line. The systems and methods include mapping application programming interfaces (APIs) to one or more applications, and based on the API mapping, determining a priority level for each of the applications. A network traffic volume for each of the APIs mapped to the applications is predicted. Based on the predicted network traffic volume and the priority level of each of the applications, the systems and methods determine a change window for taking the applications off-line.