Abstract: Disclosed is an example approach in which news alerts are scanned in real-time or near real-time, relevant alerts identified through a topic extraction model, and associated actors identified through an entity extraction model. An entity resolution model may be applied to determine which actors are clients. The topic extraction, entity extraction, and/or entity resolution models may apply, for example, natural language processing models. The alert may be enriched by being packaged with client and transactional data to generate an enriched alert. A predictive model may be applied to the enriched alert to identify events with a high probability of law enforcement referral, and the enriched alert may be automatically transmitted to certain identified devices. The predictive model is trained using a combination of news alerts and data on clients and transactions, yielding enhanced predictions.

Abstract: Disclosed is an approach in which news alerts are scanned in real-time or near real-time, relevant alerts identified through a topic extraction model, and associated actors identified through an entity extraction model. An entity resolution model may be applied to determine which actors are clients. The topic extraction, entity extraction, and/or entity resolution models may apply, for example, natural language processing models. The alert may be enriched by being packaged with client and transactional data to generate an enriched alert. A predictive model may be applied to the enriched alert to identify events with a high probability of law enforcement referral, and the enriched alert may be automatically transmitted to certain identified devices. The predictive model is trained using a combination of news alerts and data on clients and transactions, yielding enhanced predictions.

Abstract: Disclosed is an approach in which news alerts are scanned in real-time or near real-time, relevant alerts identified through a topic extraction model, and associated actors identified through an entity extraction model. An entity resolution model may be applied to determine which actors are clients. The topic extraction, entity extraction, and/or entity resolution models may apply, for example, natural language processing models. The alert may be enriched by being packaged with client and transactional data to generate an enriched alert. A predictive model may be applied to the enriched alert to identify events with a high probability of law enforcement referral, and the enriched alert may be automatically transmitted to certain identified devices. The predictive model is trained using a combination of news alerts and data on clients and transactions, yielding enhanced predictions.

Abstract: Data on entities and how they are associated with other entities may be aggregated from multiple sources and reconciled. The aggregated data may be presented in a dashboard with a graphical user interface (GUI) that represents entities (e.g., nodes) and associations (e.g., edges) as distinguishable graphical elements that are individually selectable. Different nodes/edges may have distinct graphical representations that correspond with certain characteristics of the nodes/edges. The dashboard may include multiple dynamically-updated panes that may be populated with different information depending on a user's interaction with the GUI and/or depending on information received from various sources. A first entity's connection to or involvement in certain activities may be more readily understood by interactively examining not just the first entity's relationship with a second entity, but also the second entity's relationship with a third entity which is not directly related to the first entity.

Abstract: Data on entities and how they are associated with other entities may be aggregated from multiple sources and reconciled. The aggregated data may be presented in a dashboard with a graphical user interface (GUI) that represents entities (e.g., nodes) and associations (e.g., edges) as distinguishable graphical elements that are individually selectable. Different nodes/edges may have distinct graphical representations that correspond with certain characteristics of the nodes/edges. The dashboard may include multiple dynamically-updated panes that may be populated with different information depending on a user's interaction with the GUI and/or depending on information received from various sources. A first entity's connection to or involvement in certain activities may be more readily understood by interactively examining not just the first entity's relationship with a second entity, but also the second entity's relationship with a third entity which is not directly related to the first entity.

Abstract: Disclosed is an example approach in which news alerts are scanned in real-time or near real-time, relevant alerts identified through a topic extraction model, and associated actors identified through an entity extraction model. An entity resolution model may be applied to determine which actors are clients. The topic extraction, entity extraction, and/or entity resolution models may apply, for example, natural language processing models. The alert may be enriched by being packaged with client and transactional data to generate an enriched alert. A predictive model may be applied to the enriched alert to identify events with a high probability of law enforcement referral, and the enriched alert may be automatically transmitted to certain identified devices. The predictive model is trained using a combination of news alerts and data on clients and transactions, yielding enhanced predictions.