A Study of Enrollment Projections for USA Higher Educa-tion Institutions

  • Emma Gyasi Central Michigan University
  • Felix Famoye Central Michigan University
  • Carl Lee Central Michigan University
  • Robert Roe Central Michigan University
Keywords: enrollment models, modeling techniques, predictive modeling, machine learning, data mining techniques.


This study provides results from a survey on enrollment projections, methods, metrics, timing, and model among public 2-year and 4-year higher education institutions in the United States. The data are from 127 public, 4-year and 73 public, 2-year institutions surveyed in spring and summer 2021. The results are summarized on various aspects of the process for developing enrollment projection numbers from the factors considered, the type of enrollment models used, methods and modeling techniques implemented, and the involvement of campus offices. These findings will help provide details on current enrollment models, methods and modeling techniques implemented, and campus offices' involvement in enrollment projections in higher education institutions. The study reveals, there is no vast difference in how public, 4-year and public, 2-year institutions oversee enrollment projections. Almost all institutions build and develop their enrollment models in-house. The most widely used software for modeling and presenting enrollment projections is Microsoft (MS) Excel. The top three modeling techniques implemented in enrollment projection are Time series models, Markov chain models, and Linear regression models. Multiple offices in the institutions participate in the process of producing enrollment projection numbers.

Author Biographies

Felix Famoye, Central Michigan University

Department Chairperson,

Department of Statistics, Actuarial & Data Sciences,


Carl Lee, Central Michigan University

Department of Statistics, Actuarial & Data Sciences,

Robert Roe, Central Michigan University

Executive Director,

Academic Planning & Analysis


A. Slim, D. Hush, T. Ojah, and T. Babbitt, "Predicting Student Enrollment Based on Student and College Characteristics." International Educational Data Mining Society, 2018.

D. Trusheim, and C. Rylee, "Predictive modeling: Linking enrollment and budget-ing." Planning for Higher Education vol. 40, no.1, 2011, pp. 12.

P. T. Brinkman, and C. McIntyre, "Methods and Techniques of Enrollment Fore-casting." New directions for institutional research vol. 93, 1997, pp 6780.

S. S. Aksenova, D. Zhang, and M. Lu, "Enrollment prediction through data mining." In 2006 IEEE International Conference on Information Reuse & Integration, IEEE, 2006, pp. 510515.

G. A. Kraetsch, "Methodology and Limitations of Ohio Enrollment Projections. The AIR Professional File, No. 4, Winter 1979-80.", 1979.

N. Cristianini, and J. Shawe-Taylor, An introduction to support vector machines and other kernel-based learning methods. Cambridge university press, 2000.

J. Luan, "Data mining applications in higher education." SPSS Executive 7, 2004.

B. Schölkopf, A. J. Smola, and F. Bach, Learning with kernels: support vector machines, regularization, optimization, and beyond, MIT press, 2002.

Q. Song, and S. C. Brad, "New Models for Forecasting Enrollments: Fuzzy Time Series and Neural Network Approaches.", 1993.

R. L. Armacost, and A. L. Wilson, "Three Analytical Approaches for Predicting Enrollment at a Growing Metropolitan Research University. AIR 2002 Forum Pa-per.", 2002.

N. V. Ivankova, J. W. Creswell, and S. L. Stick, "Using mixed-methods sequential explanatory design: From theory to practice." Field methods, vol. 18. no. 1, 2006, pp. 320.

A. D. Ong, and D. J. Weiss, "The impact of anonymity on responses to sensitive questions 1." Journal of Applied Social Psychology, vol. 30, no.8, 2000, pp. 16911708.

H. Gunn, “Web-based Surveys: Changing the Survey Process,” First Monday, 7. 2002: https://doi.org/10.5210/fm.v7i12.1014

Review/Survey Papers