Detecting fraudulent activity can be a complex, manual process. In this paper, we adapt statistical properties of count data in a novel algorithm to uncover records exhibiting high risk for fraud. Our method identifies shelves, partitioning data under the counts using a Student's t-distribution. We apply this methodology on a univariate dataset including cumulative results from phone calls to a customer service center. Additionally, we extend this technique to multivariate data, illustrating that the same method is applicable to both univariate and multivariate data.

The present disclosure includes systems, apparatuses, and methods for event identification. In some aspects, a method includes receiving data including text and performing natural language processing on the received data to generate processed data that indicates one or more sentences. The method also includes generating, based on a first keyword set, a second keyword set having more keywords than the first keyword set. The method further includes, for each of the first and second keyword sets: detecting one or more keywords and one or more entities included in the processed data, determining one or more matched pairs based on the detected keywords and entities, and extracting a sentence, such as a single sentence or multiple sentences, from a document based on the one or more sentences indicated by the processed data. The method may also include outputting at least one extracted sentence.

The present invention is directed to a system, comprising a first data-processing system and at least one second data-processing system, a processing component, and data-storage component. The system is configured to perform for each condition-state of at least a subset of the condition states: comparing each condition-state value and the respective condition-state threshold, thus generating a comparison result for each of these condition-states, and further assigning each comparison result to the respective condition-state. The system is further configured for generating a condition-node modifier for each condition-node of at least a subset of condition-nodes by aggregating the comparison results of the condition-states of at least the subset of the condition-states which condition-states are assigned to the respective condition-node. The invention is further directed to a corresponding computer-implemented method.

An organizational risk management service includes a risk assessment and mitigation platform for evaluating organizational risk. The service includes interfaces for managing connections with organizational and external systems for intake of messaging that provides information which is analyzed to define risks faced by an organization. This risk is defined by analyzing this messaging and its metadata with a system manager, a rules engine, and a message manager. The service and platform models responses to address the risks faced by the organization, and generates event relays that comprise communications, alerts, notifications, instructions, and other information for registered users, and external systems that enable actions for addressing and mitigating the risk and compliance with organizational policies and procedures.

Various embodiments described herein relate to performance assurance modeling for a portfolio of assets. In this regard, a request to generate one or more performance assurance insights related to one or more assets is received. The request includes a fault descriptor describing one or more faults associated with the one or more assets. In response to the request, a first risk level associated with the one or more faults is determined based on the fault descriptor and asset data associated with the one or more assets. Additionally, in response to the request, a second risk level associated with the one or more faults is generated based on one or more predetermined relationships between faults and asset performance indicator thresholds. The one or more performance assurance insights are then generated based on a comparison between the first risk level and the second risk level.

Various embodiments described herein relate to performance assurance modeling for a portfolio of assets. In this regard, a request to generate one or more performance assurance insights related to one or more assets is received. The request includes a fault descriptor describing one or more faults associated with the one or more assets. In response to the request, a first risk level associated with the one or more faults is determined based on the fault descriptor and asset data associated with the one or more assets. Additionally, in response to the request, a second risk level associated with the one or more faults is generated based on one or more predetermined relationships between faults and asset performance indicator thresholds. The one or more performance assurance insights are then generated based on a comparison between the first risk level and the second risk level.

The present application provides a method and system for dynamically predicting a deoxynivalenol content of wheat at harvest, including: on the basis of historical data, screening out by particle swarm optimization algorithm combined factors suitable for establishing a prediction model, and establishing the prediction model by using the combined factors; on the basis of data of a current year, predicting a second flowering date and a second harvest date of wheat in the current year by an agricultural model; then obtaining a weather forecast on the basis of the second flowering date and the second harvest date, and combining the weather forecast and geographic data into correlated factors; and finally predicting the deoxynivalenol content of wheat at harvest by means of the prediction model and the correlated factors. Compared with the prior art, statistical items in the prediction model are more comprehensive, and growth period data of the current year can be dynamically predicted on the basis of growth period indexes model, thus continuously adjusting and establishing the prediction model. In addition, an overhead time for screening multi-dimensional large-batch data by the particle swarm optimization algorithm has more advantages, and the prediction model established by a multiple linear regression algorithm has higher precision.

The present application provides a method and system for dynamically predicting a deoxynivalenol content of wheat at harvest, including: on the basis of historical data, screening out by particle swarm optimization algorithm combined factors suitable for establishing a prediction model, and establishing the prediction model by using the combined factors; on the basis of data of a current year, predicting a second flowering date and a second harvest date of wheat in the current year by an agricultural model; then obtaining a weather forecast on the basis of the second flowering date and the second harvest date, and combining the weather forecast and geographic data into correlated factors; and finally predicting the deoxynivalenol content of wheat at harvest by means of the prediction model and the correlated factors. Compared with the prior art, statistical items in the prediction model are more comprehensive, and growth period data of the current year can be dynamically predicted on the basis of growth period indexes model, thus continuously adjusting and establishing the prediction model. In addition, an overhead time for screening multi-dimensional large-batch data by the particle swarm optimization algorithm has more advantages, and the prediction model established by a multiple linear regression algorithm has higher precision.

Techniques for risk evaluation include receiving, from a requesting entity, a request for monitoring target entities specifying a first identifier associated with each target entity and target entity information. The system generates a second identifier and a third identifier for each target entity and stores a mapping of the second identifiers to the first identifiers and the third identifiers, preventing the second identifiers from being provided to the requesting entity. The system monitors a periodically updated data set and determines risk metrics for the target entities, comparing each risk metric to a threshold value to identify target entities whose risk data indicates an insider threat. The system generates a third identifier for the identified target entities and provides the third identifiers to the requesting entity. Responsive to a request for a corresponding first identifier, the system identifies and provides the first and third identifiers to the requesting entity.

A document execution engine receives a training set of data including training documents that each include one or more passages associated with a passage type and a level of risk. The document execution engine trains a machine learned model based on the training set. The trained machine learned model, when applied to subsequently identified passages within documents in the document execution environment, can identify a passage with above threshold levels of risk (e.g., a high-risk passage) based on a passage type of the passage. The trained machine learned model can then provide for display the high-risk passage and a related passage of the same passage type from a second document within the document execution environment to the user via a document passage comparison interface. Differences between the passages can be highlighted, enabling a user to quickly compare and contrast the passages.