Abstract: As described herein, a system, method, and computer program are provided for a financial-based recommendation engine. In use, financial-related data is gathered for a plurality of users from a plurality of sources. Additionally, the plurality of users are clustered into a plurality of cohorts, based on the financial-related data. Further, a plurality of user profiles are created for the plurality of cohorts, including for each cohort of the plurality of cohorts, creating a corresponding user profile based on the financial-related data for the users in the cohort. Still yet, each user profile of the plurality of user profiles is matched to one another and to one or more financial products. Moreover, the one or more financial products matched to each user profile of the plurality of user profiles are recommended to the users in the cohort that corresponds to the user profile.

Abstract: Methods, systems and computer program products implementing data enrichment using global structure learning are disclosed. An information enrichment system predicts a likely canonical name from a transaction record in which names may be shortened, or extra token(s) inserted. In a training phase, the information enrichment system determines tag patterns based on labeled and unlabeled training transaction records. The tag patterns include co-occurrence probability and sequential order of co-occurrence of tags. In a testing phase, the information enrichment system receives a test transaction record. The information enrichment system predicts a likely tag sequence from the test transaction record based on the tag patterns. The information enrichment system predicts a canonical name based on likely tag values and token composition. The information enrichment system can then enrich the test transaction record with the predicted canonical name.

Abstract: Performing semantic analysis on a user-generated text string includes training a neural network model with a plurality of known text strings to obtain a first distributed vector representation of the known text strings and a second distributed vector representation of a plurality of words in the known text strings, computing a relevance matrix of the first and second distributed representations based on a cosine distance between each of the plurality of words and the plurality of known text strings, and performing a latent dirichlet allocation (LDA) operation using the relevance matrix as an input to obtain a distribution of topics associated with the plurality of known text strings.

Abstract: Performing semantic analysis on a user-generated text string includes training a neural network model with a plurality of known text strings to obtain a first distributed vector representation of the known text strings and a second distributed vector representation of a plurality of words in the known text strings, computing a relevance matrix of the first and second distributed representations based on a cosine distance between each of the plurality of words and the plurality of known text strings, and performing a latent dirichlet allocation (LDA) operation using the relevance matrix as an input to obtain a distribution of topics associated with the plurality of known text strings.

Abstract: The disclosed embodiments illustrate methods and systems for processing crowd-sensed data to generate actionable insights of geographical areas. The method includes extracting the crowd-sensed data, corresponding to one or more events in a geographical area, from one or more data sources. The extracted crowd-sensed data is stored in a storage device based on at least a time, a location, and an event category associated with the extracted crowd-sensed data. The method further includes aggregating the stored crowd-sensed data based on at least the location and the event category. The method further includes rendering graphical distributions of the one or more events in the geographical area, based on at least the aggregated data, on a user interface displayed on a display screen of a computing device. The graphical distributions of the one or more events are representative of the actionable insights of the geographical area.

Abstract: A method and a system are provided for role-based auto-selection of employees for trainings associated with skills required in a project. The method comprising receiving a request for the project. The method may extract one or more current skills of one or more employees based on the received request. The method for a required role in a project may further determine, a proficiency gap between the one or more required skills and the one or more current skills for each of the one or more employees. The method for a required role in a project may prioritize the one or more required skills for each of the one or more employees based on the determined proficiency gap. The method may select a set of employees from the one or more employees for one or more skill-based trainings.

Abstract: Embodiments of a system and a method for design and implementation of an employee incentive scheme for one or more tasks are disclosed. The system includes a data input module and a unified incentive module. The data input module on a computer with a processor and a memory being configured to: receive a task for a plurality of employees from the user device; and identify whether or not a task is associated with a predetermined baseline. The task is identified as a routine task if associated with the predetermined baseline, else the task is identified as a special task. The unified incentive module on the computer is configured to compute a task incentive for at least one of the routine task and the special task associated with an employee among multiple employees.

Abstract: The disclosed embodiments illustrate methods and systems for selecting a set of resumes for a job description (JD). The method includes extracting at least a portion in each of a plurality of resumes based on a scoping criterion received from a user. The method further includes extracting one or more first features from said portion in each of said plurality of resumes. The method further includes selecting said set of resumes from said plurality of resumes based on a comparison between said one or more first features and said scoping criterion. Thereafter, the method includes displaying, by a display device, one or more second features of said selected set of resumes on a graphical user interface to said user. The method is performed by one or more microprocessors.