Utilization of Metadata and Data Models to Enhance Machine Learning

Data plays the most significant role to attain efficiency in performing a task using Machine Learning (ML) techniques. Metadata (MD) represents data of data. MD extraction and data attribute selection play a vital role in defining the performance of ML models. The study in this paper focuses on the role of MD, data attributes and data models that define the learning capability of ML to evolve with human-like capability to learn and draw inferences. To evolve with such artificially intelligent autonomous systems, the study in this paper is a preliminary step towards applying ML techniques on textual data for performing syntactic analysis, further to evolve with semantic and behavioral analysis. Based on the rigorous survey study and observations, this paper concludes with the description of the parameters to quantify the performance of ML model which are essential to define the performance characteristics of ML. The increased deployment of ML is observed in the recent Artificial Intelligence arena, and hence the study contributes towards evolving performance parameters in applications that employ ML techniquestextbf.