SYSTEMS AND METHODS OF DATA ANALYTICS

摘要

Systems and methods of data analytics, which in various embodiments enable business analysts to apply certain machine learning and analytics algorithms in a self-service manner by binding them to generic business questions that they can be used to answer in particular domains. The general approach may be to define the application of an algorithm to solve specific problems (questions) for particular combinations of a business domain and a data category. At design time, the algorithm may be linked to canonical data within a data category and programmed to run with this canonical data set. At runtime, given a dataset and its category, and a business domain, a user may choose from the corresponding questions and the system may run the algorithm bound to that question.

主权项

1. A method of performing data analytics, the method being performed on a data analytics system comprising a non-transitory computer-readable storage medium and a processor attached thereto, the method comprising:
storing, in the computer-readable storage, one or more applications, each application being associated with an algorithm, each application being further associated with canonical data indicative of a class of data to be accepted by the algorithm associated with the application; storing, in the computer-readable storage, one or more questions, each question being associated with an application; storing a user dataset associated with a domain and a data category; selecting a question from the one or more questions, the selected question being selected based at least in part on the domain and the data category of the user dataset; matching the user dataset based on the canonical data of the application associated with the selected question, the matching being performed by the processor, the matching comprising comparing one or more fields of the user dataset with the class of data indicated by the canonical data, the matching thereby producing a canonicalized dataset; executing the algorithm associated with the application, wherein the canonicalized dataset is provided as input to the algorithm; and presenting output from the algorithm to the user.