Forecasting Students’ Enrollment Using Neural Networks and Ordinary Least Squares Regression Models
Authors: Egbo, M.N, Bartholomew, D.C
Number of views: 520
Based on the presentation of dynamic and nonlinear data forecast, we discuss the difference in two approaches, Multi-layer feed-forward artificial neural networks and ordinary least squares regression for students’ enrolment forecast in FUTO, Nigeria. A simple procedure to include the Mean square error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) is proposed and tested. The result suggested that the Multi-Layer Feed-Forward Artificial Neural Networks provides better predictions for nonlinear and chaotic systems.