A novel CBR system for numeric prediction

Case-based reasoning (CBR) solves new problems by recalling and reusing the solutions to similar problems. Despite its popularity and simplicity, relatively little work has been done to improve CBR for numeric prediction. To predict numeric values accurately and efficiently, this paper develops a novel case indexing approach and a simple attribute weighting method for CBR. This study evaluates the proposed CBR system using nine well-known data sets, showing that it achieves better efficiency and accuracy than conventional CBR. This study also applies the proposed CBR system to solve the due date assignment (DDA) problem in a dynamic wafer fabrication factory to determine if it’s expected benefits can be observed in practice. Experimental results show that the proposed CBR system significantly improves job due date prediction.