Tantiprabha, P (1990) Acquisition of strategic management concepts from construction project data: An inductive learning approach. PhD thesis, University of Texas at Austin, USA.
Abstract
This research presents the development of a Strategic Concept Induction System, SCIS. The system incorporates a computer method in Artificial Intelligence, inductive learning, with a formal approach in strategic planning, a strategy formulation model, and a real construction project database, to assist management of a construction company in extracting preferred strategic concepts from completed project experience for application in a new project execution. Selection of an algorithm was made through a comparative study by experimental applications of three inductive learning algorithms: ID3, AQ, and Neural-Network, on real construction project data. ID3 was selected for integration into SCIS because of its simplicity and comparative accuracy. The implementation of SCIS was accomplished in a micro-computer environment, using Common Lisp software programs. The practicality of SCIS is demonstrated through examples of its applications on real construction project data to obtain useful concepts for managerial decision making. The examples illustrate that SCIS can be employed to assist managers' decision making in, but not limited to, the following cases: (1) identifying the management patterns that best predict classes of project performance outcomes at an early stage of a construction project, (2) predicting management actions in response to given project environments, and (3) providing evidence from the data to support a proposed statement or hypothesis. The limitations of this approach are also summarized for the benefit of future research. The limitations can be attributed to the closed world assumption, quality of data in the training examples, validity of the induced concepts, and weaknesses of the selected inductive learning algorithm.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Ashley, D B and O'Connor, J T |
| Uncontrolled Keywords: | accuracy; artificial intelligence; decision making; integration; learning; project performance; strategic management; strategic planning; training |
| Index terms: | manager, strategy, construction company, accuracy, learning algorithm, integration, decision-making, strategic management, construction project, program, evidence, acquisition, database, validity, comparative study, strategic planning, project performance, implementation, artificial intelligence |
| Subjects: | practitioner, evaluation and assessment methods, organization, contractual arrangements, production management, algorithms, research design and methodology, business, artificial intelligence, project management theory and practice, professional development, management, software systems, data management, organizational analysis, decision analysis |
| Topics: | Procurement, Risk Management, Project Management, Roles and Professions, Information Management, Research Practice, Business Strategy, Organizational Design, Digital Applications |
| Descriptive scope: | 3 PCA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here