FACILITATING DECISION-MAKING PROCESS USING A HIERARCHICAL MULTI-ATTRIBUTE MODEL (HMAM) IN MODELING RELATIONAL DATA

This work presents a novel approach that is capable of learning relational domain and generating automated hierarchical multi-attribute model (HMAM) to support the development of decision-making. In this paper, we describe the technique of generalizing data in relational domain using granularity computing as a means of data summarization to automate and support the construction of HMAM for decision-making. First, we introduce related works in relational data mining. Then, we introduce the concept of hierarchical multi-attribute model in decision modeling. We proceed by introducing our approach that uses the pattern-based aggregation approach to relational data mining and discuss the pre-processing procedure. Experimental results are presented based on the hepatitis dataset (KDD CUP 2005). The results of our analysis show that the proposed HMAM model is able to generate rules and the performance of classifier can be improved by adjusting the number of clusters generated.

[1]  Saso Dzeroski,et al.  Experiments in Predicting Biodegradability , 1999, ILP.

[2]  Efrem G. Mallach,et al.  Understanding decision support systems and expert systems , 1994 .

[3]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[4]  M. Kirsten,et al.  Distance based approaches to relational learning and clustering , 2001 .

[5]  Foster J. Provost,et al.  Aggregation-based feature invention and relational concept classes , 2003, KDD '03.

[6]  Luc De Raedt,et al.  Inductive Logic Programming: Theory and Methods , 1994, J. Log. Program..

[7]  Avi Pfeffer,et al.  Probabilistic Frame-Based Systems , 1998, AAAI/IAAI.

[8]  Ashwin Srinivasan,et al.  Feature construction with Inductive Logic Programming: A Study of Quantitative Predictions of Biological Activity Aided by Structural Attributes , 1999, Data Mining and Knowledge Discovery.

[9]  David M. Pennock,et al.  Towards Structural Logistic Regression: Combining Relational and Statistical Learning , 2002 .

[10]  James C. Bezdek,et al.  Some new indexes of cluster validity , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[11]  Foster Provost,et al.  Acora: Distribution-Based Aggregation for Relational Learning from Identifier Attributes , 2005 .

[12]  Robert T. Clemen,et al.  Making Hard Decisions: An Introduction to Decision Analysis , 1997 .

[13]  Peter A. Flach,et al.  Propositionalization approaches to relational data mining , 2001 .

[14]  Stephen Muggleton,et al.  Inverse entailment and progol , 1995, New Generation Computing.

[15]  Einoshin Suzuki,et al.  Application of PrototypeLines to Chronic Hepatitis Data , 2003 .

[16]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[17]  Arno J. Knobbe,et al.  Propositionalisation and Aggregates , 2001, PKDD.

[18]  Peter A. Flach,et al.  Comparative Evaluation of Approaches to Propositionalization , 2003, ILP.

[19]  Stefan Wrobel,et al.  Relational Instance-Based Learning with Lists and Terms , 2001, Machine Learning.

[20]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[21]  Ashwin Srinivasan,et al.  An Assessment of ILP-Assisted Models for Toxicology and the PTE-3 Experiment , 1999, ILP.

[22]  Efrem G. Wallach,et al.  Understanding Decision Support Systems and Expert Systems , 1993 .

[23]  Lise Getoor,et al.  Learning Probabilistic Relational Models , 1999, IJCAI.