Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system regenerates, by a semantic prediction machine learning (ML) model, phrases in a risk control document. The computing system then classifies, by the semantic prediction ML model, risk control features associated with the regenerated phrases. Subsequently, the computing system corrects, by a discriminative natural language processing (NLP) model, the classified risk control features based on the phrases and the regenerated phrases.

Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system regenerates, by a semantic prediction machine learning (ML) model, phrases in a risk control document. The computing system then classifies, by the semantic prediction ML model, risk control features associated with the regenerated phrases. Subsequently, the computing system corrects, by a discriminative natural language processing (NLP) model, the classified risk control features based on the phrases and the regenerated phrases.

Abstract: Disclosed embodiments may include a system that may receive an interaction message associated with an interaction a user has with an application or website, the interaction message may include an error message or a repeated action message. The system may identify, using a first machine learning model, one or more issues associated with the interaction message, retrieve one or more troubleshooting steps mapped to the one or more issues, and generate a first message comprising the one or more troubleshooting steps and a feedback request on an effectiveness of the one or more troubleshooting steps. The system may transmit the first message to the user, receive feedback from the user in response to the feedback request, and determine whether the feedback is negative. When the feedback is negative, the system may transmit a second message to a representative requesting the representative call the user.

Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system uses a generative machine learning (ML) model to transform a risk control document into sequences of words, classify risk control features associated with the sequences of words, and pair the sequences of words with the classified risk control features. The computing system then uses a natural language processing (NLP) model to identify syntactic characteristics of the sequences of words. Subsequently, the computing system uses a discriminative predictor system to correct the classified risk control features based on the identified syntactic characteristics, identify boundaries of the corrected classified risk control features, and pair the identified boundaries with the corrected classified risk control features.

Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system uses a generative machine learning (ML) model to transform a risk control document into sequences of words, classify risk control features associated with the sequences of words, and pair the sequences of words with the classified risk control features. The computing system then uses a natural language processing (NLP) model to identify syntactic characteristics of the sequences of words. Subsequently, the computing system uses a discriminative predictor system to correct the classified risk control features based on the identified syntactic characteristics, identify boundaries of the corrected classified risk control features, and pair the identified boundaries with the corrected classified risk control features.

Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically identify risk control features and entities in a risk control document. The computing system regenerates, by a semantic prediction machine learning (ML) model, phrases in a risk control document. The computing system then classifies, by the semantic prediction ML model, risk control features associated with the regenerated phrases. Subsequently, the computing system corrects, by a discriminative natural language processing (NLP) model, the classified risk control features based on the phrases and the regenerated phrases.

Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically suggest a word, phrase, or entity to complete a sequence in a risk control document. The computing system classifies, by a generative machine learning (ML) model, risk control features associated with phrases in a risk control document. The computing system then generates, by the generative ML model and based on the classified risk control features, suggested words, phrases, or entities to complete a sequence following a cursor position in the risk control document. The computing system then corrects, by a discriminative natural language processing (NLP) model with domain specific knowledge, the suggested words, phrases, or entities. Subsequently, the computing system generates, by a discriminative predictor system, an encoded sequence of word, phrase, or entity suggestions based on the cursor position, the classified risk control features, and the corrected suggested words, phrases, or entities.

Abstract: A system may receive an indication that a user is accessing an ATM, receive, from the ATM, average session duration data over a predetermined period, generate, using a machine learning model, a busyness score for the ATM based on the average session duration data over the predetermined period, and determine whether the busyness score for the ATM exceeds a busyness score threshold. When the busyness score for the ATM does not exceed the busyness score threshold, the system may cause the ATM to present, via a first graphical user interface, a default ATM experience. When the busyness score for the ATM exceeds the busyness score threshold, the system may cause the ATM to present via, a second graphical user interface, a busy ATM experience.

Abstract: Disclosed embodiments may include a system that may receive an indication that a user is accessing an ATM, receive, from the ATM, average session duration data over a predetermined period, generate, using a machine learning model, a busyness score for the ATM based on the average session duration data over the predetermined period, and determine whether the busyness score for the ATM exceeds a busyness score threshold. When the busyness score for the ATM does not exceed the busyness score threshold, the system may cause the ATM to present, via a first graphical user interface, a default ATM experience. When the busyness score for the ATM exceeds the busyness score threshold, the system may cause the ATM to present via, a second graphical user interface, a busy ATM experience.

Abstract: Disclosed embodiments may include a system that may receive an interaction message associated with an interaction a user has with an application or website, the interaction message may include an error message or a repeated action message. The system may identify, using a first machine learning model, one or more issues associated with the interaction message, retrieve one or more troubleshooting steps mapped to the one or more issues, and generate a first message comprising the one or more troubleshooting steps and a feedback request on an effectiveness of the one or more troubleshooting steps. The system may transmit the first message to the user, receive feedback from the user in response to the feedback request, and determine whether the feedback is negative. When the feedback is negative, the system may transmit a second message to a representative requesting the representative call the user.

Abstract: A system for dynamically routing customer calls. For example, the system may receive user interaction data associated with a first user using a first user device. The system may also receive a phone call from a user using a first phone number. The system may also identify the user via the first phone number. The system may determine, using a first machine learning model, whether the first user has a first emotion type based on the user interaction data. When the first user does not have the first emotion type, the system may route the first user to any call center representative. When the first user has the first emotion type, the system may route the first user to a first call center representative among one or more first call center representatives.