Asee peer logo

Artificial Intelligence Methods To Forecast Engineering Students' Retention Based On Cognitive And Non Cognitive Factors

Download Paper |


2008 Annual Conference & Exposition


Pittsburgh, Pennsylvania

Publication Date

June 22, 2008

Start Date

June 22, 2008

End Date

June 25, 2008



Conference Session

Student Recruitment and Retention

Tagged Division

Educational Research and Methods

Page Count


Page Numbers

13.222.1 - 13.222.14



Permanent URL

Download Count


Request a correction

Paper Authors


P.K. Imbrie Purdue University

visit author page

P.K. Imbrie is an Associate Professor in the School of Engineering Education at Purdue
University. He received his B.S., M.S. and Ph.D. degrees in Aerospace Engineering from Texas
A&M University. His research interests in educational research include modeling student success, modeling student team functioning, and multidisciplinary engineering education. His technical research interests include solid mechanics, experimental mechanics, nonlinear materials characterization, microstructural evaluation of materials, and experiment and instrument design.

visit author page


Joe Jien-Jou Lin Purdue University

visit author page

Joe J.J. Lin is a doctoral student in the School of Engineering Education at Purdue University. He received his M.S. degree in Industrial Engineering from Purdue University and B.S.I.E. from National Tsing-Hua University in Taiwan. He worked as a production control engineer before joining Purdue. His research interests include student success models, team effectiveness, neural network, fuzzy computing, data mining and production systems.

visit author page


Alexander Malyscheff Purdue University

visit author page

Alexander M. Malyscheff is a Postdoctoral Research Associate in the School of Engineering Education at Purdue University. He graduated as a Diplom-Ingenieur in Electrical Engineering from the Technical University Braunschweig (Germany) and received his M.S. in Electrical Engineering
and Ph.D. in Industrial Engineering (Operations Research) from the University of Oklahoma. Before joining Purdue University he worked as a Risk Analyst in Energy Trading. His research interests include modeling of student data, team effectiveness, mathematical programming, machine
learning, kernel methods, and data analysis.

visit author page

Download Paper |

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Artificial Intelligence Methods to Forecast Engineering Students’ Retention based on Cognitive and Non-cognitive Factors


Engineering students’ affective self-beliefs can be influential factors directly or indirectly affecting their academic success and career decision. This paper examines whether students’ non-cognitive factors can be used, alone or in combination with cognitive factors, in artificial neural network (ANN) models to predict engineering student’s future retention. Four ANN based retention prediction models using different combinations of non-cognitive and cognitive factors are presented. The independent variables includes survey items from nine non-cognitive constructs (leadership, deep learning, surface learning, teamwork, self-efficacy, motivation, meta-cognition, expectancy-value, and major decision) and eleven cognitive items representing student’s high school academic performance. The dependent variable (i.e., the output from these models) is the student’s retention status after one year.

Data from more than 4900 first-year engineering students from three freshman cohorts (2004, 2005, 2006) in a large Midwestern university were collected and utilized in training and testing these ANN prediction models. Among the four ANN models developed, the model combining 11 cognitive items and 60 selected non-cognitive items has the highest overall prediction accuracy at 71.3%, probability of detection (POD) for retained students at 78.7% and POD for not retained student at 40.5%. Removing the 11 cognitive items from this model, the overall prediction accuracy would drop slightly to 70.5%.

Results from training and testing the same model using student data from different cohorts indicate the ANN model’s predictive performance is generally stable across different cohort years. Also, a model trained with earlier year (2004) freshman cohort’s data has maintained its predictive power very well when tested with student data from later (2005 and 2006) cohorts.


As Thomas Friedman described in his best selling book ‘The World is Flat’1, the world has become flatter because of the numerous new technologies and developments in the past decades. Engineers in India, China or other parts of the world today are now able and eager to compete directly with the engineers from the United States. An alarming trend over the last decade is the number of engineering graduates in U.S. continues to fail to keep pace with the increasing production of engineers from our international competitors. In the report “Rising Above The Gathering Storm: Energizing and Employing America for a Brighter Economic Future” published by the National Academies in 20052, it is reported that undergraduate programs in science and engineering have the lowest retention rate among all academic disciplines. The National Academies further emphasized the importance of advances in engineering and technology, and described them as crucial to the social and economic conditions for the United States to compete, prosper, and be secure in the global community in the 21st century.

Imbrie, P., & Lin, J. J., & Malyscheff, A. (2008, June), Artificial Intelligence Methods To Forecast Engineering Students' Retention Based On Cognitive And Non Cognitive Factors Paper presented at 2008 Annual Conference & Exposition, Pittsburgh, Pennsylvania. 10.18260/1-2--4315

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2008 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015