An Exploratory Cognitive Business Intelligence System

Only available on StudyMode
  • Download(s) : 66
  • Published : April 9, 2012
Open Document
Text Preview
2007 IEEE/WIC/ACM International Conference on Web Intelligence

An Exploratory Cognitive Business Intelligence System
Li Niu*, Jie Lu§ , Eng Chew§, and Guangquan Zhang§ Faculty of Information Technology, University of Technology, Sydney, Australia * ollieniu@hotmail.com, §{ jielu, engchew, zhangg}@it.uts.edu.au Abstract An exploratory study of web-based cognitive business intelligence systems (CBIS) is presented in this paper. The underpinning concepts and theories are situation awareness, mental model, and naturalistic decision making (NDM). The CBIS is an extension of the traditional business intelligence system with cognitive orientation. It focuses on developing, enriching, and utilizing the executive’s situation awareness, mental models, and other past experience during human-computer interaction, which drives the decision process to approach a naturalistic decision. The objective of this research is to enhance the analytical functionality of traditional BI systems through extending traditional BI systems on cognitive orientation. We develop a cognitive business intelligence system to support the executive’s SA and mental models for better decision making. The CBIS is based on a data warehouse subsystem, a case base, and a mental model base. The decision-making process in the CBIS is based on RPD model.

2. Theoretical fundamentals
Situation awareness (SA) is a cognitive psychology concept. Endsley [5] suggests SA is divided into three levels of mental representations: perception (level 1 SA: perceiving raw information from the environment), comprehension (level 2 SA: understanding perceived information), and projection (level 3 SA: predicting the future status of the environment). The development process of SA is called situation assessment [5]. This process can be enhanced by means of appropriate technologies. SA is believed to be an essential prerequisite for people’s decision making in any complex and dynamic situations. Many incidents or mishaps that resulted from inadequate SA of the operator have been widely examined [5, 6, 7]. Mental models are commonly referred to as deeply held assumptions and beliefs that enable individuals to make inferences and predictions [1, 8]. Mental models are important for decision making through acting as reasoning mechanism and by affecting situation assessment. In the study of decision making, naturalistic decision making (NDM) has emerged as a new discipline since 1980s [9]. Recognition-primed decision (RPD) model is the prototypical NDM model [10]. The emphasis of the RPD model is situation awareness. When presented in a decision situation, the decision maker will try to recognize the current situation through developing concurrent SA. The recognition results in feasible 812 811

1. Introduction
Decision support systems (DSS) are envisioned as “executive mind-support systems” that are able to support decision-making process from human cognitive aspects [1]. Nevertheless the emphasis of today’s DSSs falls into either powerful data analysis functionality, or mathematical and statistical models, or efficiency of group communication [2, 3]. Cognitive orientation in DSS remains weak albeit it has long been recognized as an important consideration [1, 4]. This is also the case of business intelligence (BI) systems, a kind of data-driven DSSs, focuing on the manipulation of large volumes of company data in data warehouses. The notion of cognitive orientation grounds in cognitive psychology, of which situation awareness (SA) and mental model are two important concepts. The decision-maker’s cognitive ability (driven by SA and mental models) plays a key role for dealing with unstructured problems with time pressure, uncertainty and high personal stakes [5, 6]. The concepts of SA and mental model form the basis of naturalistic decision making (NMD) models, i.e. recognition-primed decision model (RPD).

© 2007 IEEE DOI 10.1109/WI.2007.21

goals, important cues, and potential...
tracking img