Feature Extraction Model to Identify At -- Risk Level of Students in Academia

Abstract

Since four decades, a sincere concern has aroused among managerial, professional, towards the satisfaction of teaching-learning objective in Academia. Huge span of time has already been spent revealing student's profile patterns using predictive modeling methods, however, very little effort is put up in identifying the causative features responsible for varied students' performances followed by decisive and remedial actions upon them. Data mining techniques can be used to understand the pitfalls arising in the teaching-learning professions. In machine learning feature selection or Attribute analysis is often treated as a preprocessing step. This paper proposes a framework for identify the most contributed attributes towards academia, for the performance of second year students of computer science and application course. An appropriate supervised machine learning model is applied upon our set of inherent attributes in order to arrive (NBC) at predictive scenarios for given pattern of external attributes. Thus, the model is able to extract the fitness procedure sequences of external effort put up by each student who is predicted in 'at-risk' category. The end-user can make use of these precedence relations to identify and resolve the most unfit governing factor for upgrading students' appraisals.