The Community for Technology Leaders
Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
ISBN: 978-0-7695-3507-4
pp: 671-675
Predicting student graduation rates in institutes of higher education is of great value to the institution and an enormous potential utility for targeted intervention. During the past decade a number of researchers applied various methodologies in order to predict enrollment rates, persistence rates, and/or graduation rates. In this paper we present the development and performance of an Artificial Neural Network (ANN) for predicting community college graduation outcomes as well as the results of applying sensitivity analysis on the ANN parameters in order to identify the factors that result into a successful graduation outcome. A sample of 1,407 student profiles was used to train and test our ANN. The average predictability rate for the ANN’s training and test sets were higher than any other reported in the literature (77% and 68%, respectively). The need for disability services, the need for support services, and the student’s age at the time of application to the college were identified as the three factors most contributory to a successful/ unsuccessful graduation outcome.
student graduation, persistant rate, community colleges, neural networks

S. T. Karamouzis and A. Vrettos, "Sensitivity Analysis of Neural Network Parameters for Identifying the Factors for College Student Success," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 671-675.
94 ms
(Ver 3.3 (11022016))