Methodolody to evaluate Graduates - ECS IELTS

Methodolody to evaluate Graduates

I. Bayesian Networks

 A Bayesian network [6] is a graphical representation of a probability distribution. It is a directed acyclic graph in which nodes represent random variables and links represent probabilistic influences between the variables. Probabilistic dependence and independence are expressed by the presence or lack of paths between nodes in the graph. The fact that probabilistic dependence is encoded in the network topology in this way permits probability distributions over large numbers of random variables to be compactly represented and permits calculations to be performed efficiently. Due to the inherent uncertainty of the performance prediction problem, we chose to use Bayesian networks for the modeling task. Using a probabilistic model has the advantage that it can later become a component of a higher level optimization model.

ECS IELTS coaching center in chennai

 II. Data Pre-Processing 

At AIT coursework is generally completed within the first year of study. So we used the grade point average (GPA) accumulated after the first year as the dependent variable. The numeric GPA at AIT ranges from 0 to 4.0, which is also translated into a letter grade with values of A, B+, B, C+ and Fail (C or below). The number of students classified as Fail is low due to an institute policy of continuous review of students and either special tutoring for or dismissal of students with low grades. Based on research on student performance [3, 5] and available attributes in the admission data, ten attributes were chosen as predictors of performance: age, gender, marital status, nationality, English test score, institute of the previous degree, major of the previous degree, GPA of the previous degree, field of study and degree program (master or doctor) to which the applicant is applying. The attributes major and field of study (FoS) have a large number of values so they were processed by clustering the values into groups of similar majors and similar fields of study.
The attributes nationality and institute of the previous degree have large numbers of values (86 and 1700, respectively) without any intrinsic meaning. We thus decided to transform them into more meaningful values. The socio-economic environment can play a major role in the performance of students. So we used the World Bank classification of countries according to their Gross National Income (GNI) to group countries into GNI categories of LIC (Low Income), LMC (Low Middle Income), UMC (Upper Middle Income), NOC (High Income, non-OECD), and OEC (High Income, OECD). The most significant factor concerning the university of the previous degree is the quality of the academic programs there. http://ecsielts.com/ We gauged this by correlating the GPA of the previous degree with that obtained at AIT. If students consistently enter AIT with somewhat average grades from a particular university but graduate with high grades, we take this difference as evidence of the high quality of that institution and vice versa otherwise. To account for the nonlinear nature of the grading scale at AIT, the GPA distance was calculated by the difference between the incoming GPA and the squared outgoing GPA from AIT. We rated institutions on continuous scale from 1 to 100. With this rating scale, we found that universities offering primarily programs in economics and social sciences were getting ranked quite highly.

https://www.facebook.com/ECS-IELTS-Coaching-Centre-In-Velachery-ChennaiPTESpoken-EnglishTEFL-1292612217562388/