A STUDY OF PREPROJECT PLANNING AND PROJECT SUCCESS USING ANN AND REGRESSION MODELS

摘要

It is long recognized by the industry practitioners that how well preproject planning is conducted has great impact on project outcome. Through industry project data collection and model analysis, this research intends to investigate the relationship between preproject planning and project success. In early stage of the project life cycle, essential project information is collected and crucial decisions are made. It is also at this stage where risks associated with the project are analyzed and the specific project execution approach is defined. To assist with the early planning process, Construction Industry Institute (CII) has developed a scope definition tool, Project Definition Rating Index (PDRI) for industrial and building industry. Since its introduction, PDRI has been widely used by the industry and researchers have been using the PDRI to collect preproject planning information from the industry. Scope definition information as well as project performance are collected and used for this research analysis. This research summarizes preproject planning data collected from 62 industrial projects and 78 building projects, representing approximately $5 billion in total construction cost. Based on the information obtained, preproject planning was identified as having direct impact on the project success (cost and schedule performance). Two techniques were then used to develop models for predicting cost and schedule growth: statistical analysis, and artificial neural networks (ANN). The research results provide a valuable source of information for the industry practitioners that proves better planning in the early stage of the project life cycle have positive impact on the final project outcome.