Decision-making in industry can be focused on different types of problems. Classification and prediction of decision problems can be solved with the use of a decision tree, which is a graph-based method of machine learning. In the presented approach, attribute-value system and quality function deployment (QFD) were used for decision problem analysis and training dataset preparation. A decision tree was applied for generating decision rules.
Part of the book: Graph Theory
The chapter discusses problems of the product configuration process and application of chosen methods to represent the knowledge related to this process. One of the most important issues in product life-cycle management is to identify customer needs and combine them with product’s technical and trade characteristics. The main tasks related to product configuration are focused on identifying the most suitable product to a particular customer, product decomposition, and estimating product characteristics. In the presented approach, identification of customer needs was discussed, and a product decomposition method was presented. The quality function deployment (QFD) method was suggested to be applied as a product and production process data integration tool, where engineering characteristics of a product are combined with its trade characteristics.
Part of the book: Product Lifecycle Management
The graph theory is a well-known and wildly used method of supporting the decision-making process. The present chapter presents an application of a decision tree for rule induction from a set of decision examples taken from past experiences. A decision tree is a graph, where each internal (non-leaf) node denotes a test on an attribute which characterises a decision problem, each branch (also called arc or edge) represents the outcome of a test (attribute value), and each leaf (or terminal) node holds a class label which can be interpreted as a decision type. In the presented approach, the object-attribute-value (OAV) framework will be used for decision problem characteristics. The chapter presents a method of optimal decision tree induction. It discusses the Iterative Dichotomiser 3 (ID3) algorithm and provides an example of the decision tree induction. Also, rules supporting the decision-making in engineering will be developed in this chapter.
Part of the book: Application of Decision Science in Business and Management