Abstract: Systems and techniques for dynamic memoryless demand-supply pegging are described herein. An identification may be received of a demand to be pegged. An inventory may be determined for a material node at a time bucket. A set of other demands may be identified for the material node at the time bucket. A quantity to be pegged may be calculated. A quantity to skip may be calculated based on a sum of demand units corresponding to members of the set of other demands having a lower priority than the demand. A supply set of units may be identified. A pegged subset of the supply set of units may be generated by skipping members of the supply units equal to the quantity to skip. A graphical representation of the supply set of units for the time bucket may be output including identification of members of the pegged subset.

Abstract: Systems, and methods for selecting advertisements based on party size and/or engagement are provided. An Internet-connected media display device may be detected as displaying media. An up-to-date party size in a monitored space may be determined based on frequency response data by a wireless access point located close to the space. An up-to-date engagement level may also be determined with respect to each individual in the space based on frequency response data by the wireless access point. An advertisement database may be filtered for a qualifying advertisement based on the identified party size and engagement levels.

Abstract: A method and apparatus for processing risk-management feature factors based on user generated content (UGC), an electronic device and a storage medium are disclosed, which relates to the fields of artificial intelligence and cloud computing. An implementation includes generating a feature expression of the UGC based on the UGC; and extracting the risk-management feature factors of the UGC according to a pre-generated risk-management-feature-factor extracting model and the feature expression of the UGC.

Abstract: Systems and methods are provided for managing organizational or corporate structures, including the employee roles or activities administered by human resources. A portion of the role datasets received within human resource records may be used to generate role tokens comprising unique datasets that have been truncated and deduped. Such tokens may be extracted based on assigned prioritization scores, and further assigned training labels representing categorical levels. Predictive labels may be assigned to a remaining portion of the extracted tokens via a logistic regression classifier, and a model organizational dataset may be generated based on the assigned training labels and the assigned predictive labels. The prediction certainty of the role tokens in the model organizational dataset may be used to map the identified role tokens to the roles represented in the human resource records.

Abstract: A computer-implemented method can receive a new plan deviation alert having a deviation level that quantifies a mismatch between expected supply chain parameters specified by a supply chain plan and observed supply chain parameters. Responsive to the new plan deviation alert, the method can perform a rule-based search to find a plurality of potential remediation solutions to correct the mismatch. The method can simulate implementation of the potential remediation solutions and evaluate expended resources associated with them. Based on the evaluated expended resources, the method can generate a ranked list of candidate remediation solutions and display the ranked list of candidate remediation solutions in a user interface. The method can receive a selected remediation solution from the ranked list of candidate remediation solutions for initiation. Machine learning can be used on an expert user's selection to adapt to the expert's preferences and provide more relevant remediation solutions.

Abstract: Systems and methods disclosed herein provide automatic expense categorization of transactions or expenditures based on a machine learning (ML) model trained using anonymized transactional data for expenditures that are stored in a public blockchain. The anonymized transactional data for the expenditure and the expense category, may be distributed throughout the blockchain network and recorded in the blockchain. In some implementations, an expenditure may be submitted to the blockchain network for expense categorization. The transactional data for the expenditure may be anonymized to remove confidential and personal identifying information (PII) before it is distributed throughout the blockchain network. Each participating node of the blockchain network may utilize the ML model to identify an expense category for the expenditure. The participating nodes may provide a consensus mechanism in order to arrive at a shared understanding of how to categorize the expenditure.

Abstract: Computer-implemented functionality is described herein for assisting a user in interacting with an environment. In one implementation, the functionality operates by: determining that a particular user is within a prescribed proximity to an electronic sign, or will be in prescribed proximity to the electronic sign, based on sensor information provided by one or more sensors within the environment; determining an identity of the user; determining at least one destination of the user based at least on calendar information; providing directions to the destination(s), to provide unfiltered direction information; optionally filtering the unfiltered direction information with respect to restriction information (e.g., privacy information, security information, etc.), to produce filtered direction information; composing sign information based on the filtered direction information; and sending the sign information to the electronic sign for presentation by the sign.

Abstract: Systems and methods for determining a risk of damage to a crop on an agronomic field are described. In an embodiment, a computer system receives, for each hour of a first day, weather data identifying temperature values and humidity values associated with a geographic location. The computer system determines, for a particular hour of the first day, that a temperature value is within a first range of values and a humidity value is within a second range of values and, in response, identifies the particular hour as a risk hour. The computer system computes, for a second day, a risk value for one or more agronomic fields at the geographic location based, at least in part, on one or more identified risk hours between a day of planting a crop on the one or more agronomic fields and the second day.

Abstract: A system and method are disclosed for solving a hierarchy of objective functions using one or more hierarchical optimizations using explanation data stored in a database according to the one or more hierarchical optimizations, retrieving the explanation data, generating a response to a query for a goal violation by parsing the retrieved explanation data, and displaying the response.

Abstract: This disclosure relates generally to method and system for forecasting sales based on N-Gram model. The present disclosure provides accurate prediction of sales for optimal operations to reduce the cost. The method receives a plurality of inputs of each product comprising a sales history, and a current price bin. The categorical sale(s) for each product is discretized based on the sales history by clustering each product sales history into a one or more groups based on a maximum sales velocity range. Further, a probability table is generated for the discretized categorical sales of each product based on computing a round off weighted mean and a median using a N-Gram model. Then, a smooth probability table is computed for the generated probability table. To forecast sales multistep prediction for the smooth probability table is computed based on at least one of a joint approach, a bootstrapped approach, and a step greedy approach.

Abstract: The disclosed embodiments provide a system for performing sequence modeling for searches. During operation, the system obtains a sequence of jobs associated with activity by a member of an online system. Next, the system applies a word embedding model of a set of job histories to attributes of individual jobs in the sequence of jobs to produce embeddings for the individual jobs. The system then generates a set of power means from the embeddings. Finally, the system outputs the set of power means as an encoded representation of the sequence of jobs, wherein the set of power means is used in generating job recommendations related to the member.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to collect and analyze driver rating information. An example apparatus includes at least one of an audio input device or a video input device to collect at least one of audio or video; a rating input device to receive a rating associated with a person; a first rating analyzer to analyze the at least one of the audio or the video to determine demographic information for the person; and a second rating analyzer to: analyze the demographic information, the rating, and historical rating information to detect a demographic trend in the rating information; and output an indication of the trend.

Abstract: A computer-implemented position-centric personnel modeling apparatus, system, and method may be provided. A nodal hierarchy may be created to correlate with the personnel structure of a business enterprise, wherein each node may be a cyberspace representation of an individual within the personnel structure of the business enterprise. Attributes correlating to individual personnel in the business enterprise may be mapped to a respective node. Objectives may subsequently be tasked within the model and the nodal hierarchy may be rearranged based on the results. Results from the model may optionally be reflected by a business enterprise.

Abstract: An enterprise risk management (ERM) system performs real-time self-diagnosis of functional code of the ERM system that controls the policy enforcement actions within the ERM system. Real-time execution effectiveness of at least one control instance of the ERM system at operationally mitigating real-time authentication services security risk(s) and user access compliance risk(s) is determined. At least one code modification to a control class definition is identified that adjusts one or more real-time operational control aspects of the at least one control instance and that improves real-time execution effectiveness and operational capabilities of a new control instance instantiated from an updated control class definition at operationally mitigating the respective real-time authentication services security risk(s) and user access compliance risk(s) within the ERM system.

Abstract: Aspects of the invention include receiving, using a processor, a plurality of values of a performance indicator. A statistical analysis of the plurality of values of the performance indicator is performed, using the processor, to detect an anomaly pattern in the plurality of values of the performance indicator. A warning message about the detected anomaly pattern is sent to an alert recipient that is selected by a machine learning model trained to identify alert recipients based at least in part on detected anomaly patterns. Feedback about the warning message is received from the alert recipient. The feedback includes an interest of the alert recipient in receiving warning messages about the detected anomaly pattern. The machine learning model is updated based at least in part on the feedback.

Abstract: A method including retrieving a product information from a database is provided. The method includes associating the product information with multiple classification values, forming a vector associated with a consumer product. The classification values form coordinates of the vector in a vector space that comprises multiple vectors associated with multiple consumer products. The method includes determining a cluster in the vector space, including at least one vector selected according to a relative distance within a cluster boundary. The method includes selecting a discriminator vector from a vector difference between a first vector in a first cluster in the vector space and a second vector in a second cluster in the vector space and identifying a new consumer product associated with a new vector that is formed by adding the discriminator vector to a third vector from the vector space, the third vector associated with a known consumer product.

Abstract: A customer risk trigger associated with a customer may be identified. A response to the customer risk trigger may be detected. First risk analysis data related to the customer risk trigger may be gathered, based on the response, from a first datastore. Second risk analysis data related to the customer risk trigger may be gathered, based on the response, from a second datastore. A customer risk profile to model risk attribute(s) of the customer may be gathered. The risk attributes may represent a risk correlation between the customer and a prohibited act. Customer risk visualization tool(s) configured to facilitate visual user interaction with the customer risk profile may be gathered. The customer risk visualization tools may be rendered in a display of the computing system. The customer risk visualization tools provide a customer-centric view of risk for various applications, including anti-money laundering applications.

Abstract: A system and method for identifying a probability of disease affecting a crop based on data received over a network is described herein, and may be implemented using computers for providing improvements in plant pathology, plant pest control, agriculture, or agricultural management. In an embodiment, a server computer receives environmental risk data, crop data, and crop management data relating to one or more crops on a field. Agricultural intelligence computer system 130 computes one or more crop risk factors based, at least in part, the crop data, one or more environmental risk factors based, at least in part, the environmental data, and one or more crop management risk factors based, at least in part, on the crop management data.

Abstract: An apparatus for activity networking, comprising: a memory coupled to at least one processor, the processor being configured to: transmit, to a server, a request to form a crew, the request including an indication of an activity associated with the crew, an indication of a time for performing the activity, and an indication of a number of available spots on the crew; receive from the server a message indicating that all spots on the crew are occupied by a plurality of users; and provide the plurality of users with a calendar appointment for the activity.

Abstract: Modifications to the DiD technique are disclosed which provide an estimate of the effectiveness of a site-wide action where no control group exists within the data subsequent to implementation of the site-wide action. In some examples, a method may include identifying a treatment group based on a modified treatment period, selecting a control group from a control period prior to the modified treatment period, and performing a modified difference-in-differences (DiD) estimation for a metric based on the modified treatment period, the treatment group, the control period, and the control group. The modified treatment period may encompass an intervention of a site-wide action, and include a pre-intervention time period and a post-intervention time period.