In this chapter, data mining and knowledge discovery (DMKD) is presented with basic concepts, a brief history of its evolution, mathematical foundations, and usable techniques, along with the data warehouse and the decision support system (DSS). First, dataset and knowledge will be defined and elucidated as under DMKD. DMKD is a discovery process with different hierarchies, granularities, and/or scales. For a set of concepts that may be best understood if being viewed and explained from various perspectives, the chapter starts with a definition followed by a table explaining DMKD from different views (Sect. 5.1). The evolution of DMKD is then briefly tracked from the rapid advance in massive data to the birth of DMKD (Sect. 5.2). Some mathematical foundations are given in Sect. 5.3, i.e. probability theory, statistics, fuzzy set, rough set, data fields, and cloud models. Section 5.4 introduces some usable DMKD techniques. DMKD is used to discover a set of rules and exceptions with association, classification, clustering, prediction, discrimination, and exception detection. In Sects. 5.5 and 5.6, data warehouses and decision support systems are given. The first one mentioned is one of the data sources for DMKD, and DMKD is a new technique to assist the latter with a task. Finally, trends and perspectives are summarized and forecasted into two promising fields, web mining and spatial data mining (Sect. 5.7).

Data Mining and Knowledge Discovery

An Introduction to Bayesian Inference and Decision

In an effort to achieve a competitive advantage via cost reductions and improved market responsiveness, organisations are increasingly employing outsourcing as a major component of their supply chain strategies. However, as organisations increase their dependence on the suppliers of outsourced raw materials and components, they become more susceptible to their risk profiles. Supplier risk profiles are comprised of risk events which are associated with the supply network, internal operations, or external factors. Suppliers with a high probability of risk event occurrences can have a substantial impact on an organisation's revenue stream. Thus, it is essential that organisations have the means to analyse the risks associated with a supplier of outsourced materials. This article presents a methodology for analysing risks in supply networks to facilitate outsourcing decisions. The methodology includes the development of a risk profile for a given supplier through the creation of Bayesian networks. The network...

/pdf/analysing-risks-in-supply-networks-to-facilitate-outsourcing-5hqkh4vohn.pdf

Analysing risks in supply networks to facilitate outsourcing decisions

The present disclosure includes systems and techniques relating to representation and retrieval of data structures in databases. In general, embodiments of the invention feature a computer program product and a method including storing a generalized directed acyclic graph (DAG) in a database, wherein the storing includes encoding path information of the generalized DAG in entries of a path table in the database, the encoding includes converting the path information into text strings, and the entries of the path table correspond to paths in the generalized DAG from nodes of the generalized DAG to a root node of the generalized DAG; triggering generation of a lexical index of the path table using the text strings, wherein the lexical index separately lists tokens included in the entries; and retrieving one or more portions of the generalized DAG from the database for in-memory operations.

System and method of efficiently representing and searching directed acyclic graph structures in databases

Purpose – As organizations increase their dependence on supply chain networks, they become more susceptible to their suppliers’ disaster risk profiles, as well as other categories of risk associated with supply chains. Therefore, it is imperative that supply chain network participants are capable of assessing the disaster risks associated with their supplier base. The purpose of this paper is to assess the supplier disaster risks, which are a key element of external risk in supply chains. Design/methodology/approach – The study participants are 15 automotive casting suppliers who display a significant degree of disaster risks to a major US automotive company. Bayesian networks are used as a methodology for examining the supplier disaster risk profiles for these participants. Findings – The results of this study show that Bayesian networks can be effectively used to assist managers in making decisions regarding current and prospective suppliers vis-a-vis their potential revenue impact as illustrated throug...

Assessing disaster risks in supply chains

Bayesian Networks are an important area of research and application within the domain of Artificial Intelligence. This paper explores the nature and implications for Bay esian Networks beginning with an overview and comparison of inferential statistics with Bayes’ Theorem. The nature, relevance and applicability of Bayesian Network theory for issues of advanced computability form the core of the current discussion. A number of current applications using Bayesian networks are examined. The paper concludes with a brief discussion of the appropriateness and limitations of Bayesian Networks for human-computer interaction and automated learning.

I. S. P. Daryle Niedermayer

Papers

An Introduction to Bayesian Networks and Their Contemporary Applications