Institutional Repository
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Inductive learning support for decision making

Moustakis Vasilis, George Potamias

Full record


URI: http://purl.tuc.gr/dl/dias/08AF5882-6F35-4806-B21F-AA972D21227A
Year 1993
Type of Item Conference Short Paper
License
Details
Bibliographic Citation V. Moustakis, G. Potamias. (1993). Inductive learning support for decision making. Presented at 3rd International Workshop on Artificial Intelligence in Economics and Management. [Online]. Available: http://users.ics.forth.gr/~potamias/home_page/p3.pdf
Appears in Collections

Summary

In this paper we review the applicability of representative inductive machine learningapproaches in multicriteria decision making. We limit our review to four systems. We useSICLA and KBG as representative conceptual clustering systems and ID3 and CN2 asrepresentative learning from examples systems. We demonstrate our results by way of tworeal world decision making exemplars. The first exemplar concerns the evaluation of retailoutlets [15]. The second exemplar concerns venture capital assessment [16]. We discuss theconditions under which inductive learning methodologies can be effectively implemented tosupport decision making.Inductive machine learning was pioneered by Michalski [9]. It aims at the derivationof knowledge from a set of observations, or facts. In cases where facts are known to belongto a certain class we speak of concept acquisition or learning from examples. In suchan instance we target our inquiry towards the derivation of concept identification rules.Rules may be either discriminant or characteristic. When concept classes underlying factmembership are not known we speak of learning from observations, or conceptual clustering.Accordingly, we look forward toward the partitioning of facts into a meaningful and disjointset of clusters. A cluster represents a “coming together in space and time so that the densityof whatever is clustered contrasts with the density around” [6, p.33]. Generalization andspecialization are essential processes when making inductive inferences. The basic premisecharacterizing any inductive inference is falsity preservation. The derivation of a hypothesisH from facts E is falsity preserving in the sense that “if some facts falsify E, then theymust also falsify H” [9, p.89].Although inductive machine learning is a rather new field there are several andsuccessful ‘fielded’ applications [7, 8]. Carter and Catlett [2] propose a methodology forcredit card assessment using inductive learning techniques. Also, Shaw and Gentry [14]present an approach for company risk assessment that is based on inductive learning. Bothapplications are exploratory; they, however, stress the potential of inductive learning indecision making support. We maintain that learning is a trait of decision making: “quiteoften the decision maker is interested in finding out what his weights are or what theyshould be under different decision circumstances. In this sense, the weights of importancecould be considered as desirable outputs rather than independent inputs of an analysis.Weights must be revealed or learned through a careful interactive process”, [17, p.22] -emphasis is ours.In this paper we discuss the methodological issues underlying the application ofinductive learning techniques in business decision making. We limit our endeavor to fourrepresentative and well-known inductive learning systems, ID3 [12, 11, 13], CN2 [5, 4], KBG[1] and SICLA [3]. These systems are part of the Machine Learning Toolbox [7, 18]. Weexplore inductive system suitability by way of three decision making exemplars. We drawour exemplars from retail outlet evaluation and venture capital assessment. We target ourinquiry toward the evaluation of pros and cons, concerning the application of the selectedinductive learning systems, in real world business decision making. Specifically, our researchfocuses around the following lines:1. Grouping of alternatives into disjoint cluster groups. We use a Lexicographic EvaluationFunctional, LEF, criterion to optimize clustering [10].2. Identification of the most significant criteria for either alternative discrimination oralternative characterization. Suppose that we have two alternative courses of action,a1 and a2. We are interested in differences between a1 and a2, or in what a1 and a2are all about. Furthermore, we present a methodology for inducing criteria weights.3. Identification of relevant and accurate discrimination and recognition rules. We associatethis line with the previous one.4. Identification of the most representative alternative for each decision class. We steerour venture in the direction of deriving a conceptual indexing scheme for alternativecourses of action.5. Identification of bias and error resulting from contextual factors. We define contextto represent the decision making environment.Furthermore, we explore the implications of our research in decision making. Weplace emphasis upon the expert critiquing and case based reasoning paradigms.

Available Files

Services

Statistics