Development and evaluation of a tree-indexing approach to improve case-based reasoning: illustrated using the due date assignment problem

Abstract

In this study a novel case indexing approach is proposed for case-based reasoning (CBR). This new approach, called the tree-indexing approach, is a modified form of the inductive learning-indexing (IL-indexing) approach and is especially applied to assist CBR in numeric prediction. The tree-indexing approach organizes the cases in the memory by inducting a tree-shaped structure, in order to improve the efficiency and effectiveness of case retrieval. The experiments, using three real world problems from the UCI repository, show that the CBR with the tree-indexing approach (T-CBR) is superior to the conventional CBR. This study also applies T-CBR for solving the due date assignment problem in a dynamic job shop environment in order to investigate whether T-CBR's expected benefits can be observed in practice. The results of the experiments show that our proposed T-CBR can indeed more accurately predict the job due date than the other methods presently in use.