A Hybrid SLIQ–SPRINT Framework For Intelligent Faculty Workload Assignment

Abstract

The objective of the study focuses on the design and development of an innovation in the faculty workload system of Isabela State University. At present, the Scalable Parallelizable Induction of Decision Tree or SPRINT algorithm is being used; however, the algorithm had a weakness for classifying attributive lists and has high computational cost in calculating attribute segmentation. This study was specifically undertaken to address this flaw in the SPRINT algorithm. To do this, the SPRINT algorithm classification approach uses the SLIQ pre-sorting technique to answer the rewrites and resorts of the attribute lists.

 Employing the design-based research model, the problem with the current system was grounded accordingly through personal assessment and literature study. From there, system development was done, integrating the SLIQ pre-sorting technique into the SPRINT algorithm. The enhanced system was named E-SPRINT. Initial testing indicated an improvement, specifically in the time spent in classifying attribute lists.