Predictive Regression Modeling for Forecasting Graduation Duration in Online Offsite Degree Program

Abstract

The demand for Information Technology (IT) professionals continues to rise across various sectors, where they
play vital roles. However, the supply of IT graduates often fails to meet industry needs and this is a huge problem for the Sri
Lankan IT Industry (National IT-BPM Workforce Survey – 2019). In this context, this study presents a predictive regression
modelling approach to predict graduation duration in the Bachelor of Information Technology (BIT) degree program at the
University of Moratuwa, Sri Lanka. It integrates demographic data—student district, birth year, AL results, OL maths grade,
gender, employability status, occupation, and AL stream—along with academic performance indicators like diploma
completions and higher diploma completions. After evaluating the suggested features, the key findings indicate the
significance of certain features, notably the number of semesters taken to complete the diploma, higher diploma, and the
degree. Additionally, demographic factors such as district, birth year, AL results, OL maths grade, gender, and employability
status were found to be important. The regression analysis was carried out using the Orange data mining tool (Orange Data
Mining). Various algorithms, including random forest, neural network, linear regression, and k-nearest neighbours (kNN),
were used to develop predictive models. By adjusting parameters such as metrics, weights, number of neighbours, number
of iterations, and training dataset size, the models were optimised to better fit the dataset. Training and testing the models
revealed consistent error metrics, including MSE, RMSE, MAE, and R^2, validating the accuracy of predictions. By
considering the least and reasonable error in each model, the most suitable model to fit the given dataset was selected.
The prediction model accurately forecasted graduation duration for subsequent academic batches, demonstrating its
effectiveness in predicting student progress in the program. This research contributes to understanding the factors
influencing graduation duration in a distance learning context and provides insights for educational institutions to optimise
program planning and student support initiatives. Additionally, it is a good indicator to the companies to gain a better
understanding of the availability of future workforce.