Shrestha, Rabin (2024) Prediction of cost and schedule changes in transportation projects through historical bid and change order document analysis – using Oklahoma dot project cases. PhD thesis, University of Nevada, Las Vegas, USA.
Abstract
Construction bid documents encompass project specifications, drawings, schedules, and other critical details and are the foundation for project bidding and execution. Accurate bid documents are essential to ensure project bids are competitive, realistic, and aligned with requirements. However, bid documents are susceptible to risks from various sources. Failure to identify and rectify these risks can result in inaccurate cost estimates and higher bids. Therefore, identifying and resolving risks within bidding or contract documents are of utmost importance. While prior research has shed light on potential risk factors within the bid documents, a noticeable gap remains in the literature regarding identifying bid document-related risks through document-based analysis. Moreover, quantifying project cost and schedule variation remains a challenge. This study identifies bid document-related risks by analyzing pre-bid Request for Information (RFI) and quantifies project cost and schedule changes from change order documents. This study has two primary objectives: 1) identifying substantial bid document-related risks and 2) developing an automated model using Natural Language Processing (NLP) to assess cost and schedule changes for new projects. Historical bid and change order documents obtained from the Transportation-related projects of the Oklahoma Department of Transportation (DOT) are used to fulfill these objectives. The findings of this study showed that 'pay item omission' and 'incorrect quantities' are the most significant bid document-related risks for these transportation-related projects. This study enhances our understanding of risk likelihood and the specific risk types before bidding. The study also proposed a prediction model that gives an F1 score of 79% to forecast changes in cost and 72% for predicting schedule changes, achieving an overall prediction accuracy of 75.5% for cost and schedule changes. This result shows that the proposed model adequately forecasts cost and schedule changes from bid and change order documents. Since the model training and validation are carried out using transportation projects from Oklahoma DOT, the findings might not universally apply to all projects and all locations. However, the proposed methodology can be extended to various projects and adapted to suit different contexts with necessary modifications.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Lee, Jeehee |
| Index terms: | specification, drawing, transportation project, prediction model, accuracy, project cost, variation, methodology, contract document, validation, documents, bidding, document analysis, change order, risk factor, cost estimate |
| Subjects: | infrastructure and transport systems, economics, professional development, contractual condition, technical documentation, financial and cost management, prediction and forecasting, data science, environmental hazards, research methods, bidding |
| Topics: | Research Practice, Information Management, Cost Management, Contract Administration, Design Practice, Procurement, Sustainability, Engineering Principles |
| Descriptive scope: | 4 PCTA |
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