Abstract: A system and method for disambiguating entities for managing customer relationships are described. An entity disambiguation computer receives information associated with candidate entities in an entity database. The received information comprises multiple versions of attributes related to one or more entities. Attributes are disambiguated and extracted from the information. A set of timeslice objects representing the multiple versions of each attribute is created. A subset of timeslice objects is selected for comparison based on an overlap between durations in respective timeslice objects. The system and method use a similarity model comprising weight and biases assigned to sets of previously used overlapping durations to predict if the subset of timeslice objects corresponds to the same entity. The subset of timeslice objects is merged if predicted to correspond to the same entity. This merging of timeslice objects disambiguates the information present in the entity database.

Abstract: Systems and methods for disambiguating company profiles are disclosed. The system builds a database of candidate companies with timed attributes. The system further ingests timed company metadata using a PostgreSQL database. The system disambiguates location and geocoding by matching text patterns and cross-referencing one or more identified location components against one or more geocode databases and classifies and disambiguates company name component from a company name associated with the company using a conditional random field (CRF) model. Further, the system disambiguates employee attributes using a Latent Dirichlet Allocation (LDA) topic model algorithm and train a tree model for pre-selection of candidate companies for the company. The system trains a similarity model for comparison of the candidate companies and in response to a determination that two given candidate companies are same merge the company profiles associated with the given candidate companies.

Abstract: Systems and methods described herein enable effective and accurate modeling of a set of existing data profiles, perform categorization of the data profiles in an explainable way such that actions can be taken on the information to have predictable results. The systems and methods further facilitate means to categorize small text components, trained over dependent and independent model sets, to enable a cleaner and more explicit representation of information rich short-strings, in order to facilitate a more meaningful representation of the data profiles.

Abstract: Systems and methods for generating best next communication policies, for a time step of an exchange of electronic documents, fit over historical exchanges, optimizing to maximize a probability of achieving a quantified objective leveraging weighted sampling. In a preferred embodiment an electronic document is segmented whereby each constituent segment is deconstructed as a composition of custom expression varieties, pre-defined to enable fulfilment of an objective within a theme of correspondence, associating each expression with a semantic vector. A set of expression extraction models is trained independently and then a second set with knowledge of parallel label predictions, iterating to convergence. The expression compositions and associated semantic vectors are combined into a single vector for each segment. The segment vectors are appended onto profile vectors for the exchange parties, yielding a time series of profile-content vectors.

Abstract: Systems and methods for generating best next communication policies, for a time step of an exchange of electronic documents, fit over historical exchanges, optimizing to maximize a probability of achieving a quantified objective leveraging weighted sampling. In a preferred embodiment an electronic document is segmented whereby each constituent segment is deconstructed as a composition of custom expression varieties, pre-defined to enable fulfilment of an objective within a theme of correspondence, associating each expression with a semantic vector. A set of expression extraction models is trained independently and then a second set with knowledge of parallel label predictions, iterating to convergence. The expression compositions and associated semantic vectors are combined into a single vector for each segment. The segment vectors are appended onto profile vectors for the exchange parties, yielding a time series of profile-content vectors.

Abstract: Systems and methods for generating best next communication policies, for a time step of an exchange of electronic documents, fit over historical exchanges, optimizing to maximize a probability of achieving a quantified objective leveraging weighted sampling. In a preferred embodiment an electronic document is segmented whereby each constituent segment is deconstructed as a composition of custom expression varieties, pre-defined to enable fulfilment of an objective within a theme of correspondence, associating each expression with a semantic vector. A set of expression extraction models is trained independently and then a second set with knowledge of parallel label predictions, iterating to convergence. The expression compositions and associated semantic vectors are combined into a single vector for each segment. The segment vectors are appended onto profile vectors for the exchange parties, yielding a time series of profile-content vectors.

Abstract: Systems and methods for generating best next communication policies, for a time step of an exchange of electronic documents, fit over historical exchanges, optimizing to maximize a probability of achieving a quantified objective leveraging weighted sampling. In a preferred embodiment an electronic document is segmented whereby each constituent segment is deconstructed as a composition of custom expression varieties, pre-defined to enable fulfilment of an objective within a theme of correspondence, associating each expression with a semantic vector. A set of expression extraction models is trained independently and then a second set with knowledge of parallel label predictions, iterating to convergence. The expression compositions and associated semantic vectors are combined into a single vector for each segment. The segment vectors are appended onto profile vectors for the exchange parties, yielding a time series of profile-content vectors.

Abstract: A system and method for inferring an organizational structure of a record based on position role transitions from a parsed plurality of record profiles using machine learning techniques described herein. A piece-wise graph of transitions between positions across a normalized user employment landscape are computed to recover properties of user hierarchical structures across a plurality of position information by analysis of transition trajectories.