A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Using Classification Rules to Develop a Predictive Indicator of Project Cost Overrun Potential from Bidding Data
Using highway-bidding data from Texas highway projects several different ratios were calculated to describe relationships between the submitted bids such as the spread of the submitted bid and the difference between the low bid and the second lowest bid. Elevated levels of these ratios have been found to be associated with projects that have significant deviations between the original low bid amount and the completed project cost. The Ripple Down Rule (Ridor) classification algorithm was used to generate a set of rules from the database of bidding ratios that provides a prediction of the expected level of cost increase over the initial low bid price. The classification rules generated by the Ridor algorithm are presented. A test set was used to determine the usefulness of the generated rules in predicting project cost increases and results of the testing are presented.
Using Classification Rules to Develop a Predictive Indicator of Project Cost Overrun Potential from Bidding Data
Using highway-bidding data from Texas highway projects several different ratios were calculated to describe relationships between the submitted bids such as the spread of the submitted bid and the difference between the low bid and the second lowest bid. Elevated levels of these ratios have been found to be associated with projects that have significant deviations between the original low bid amount and the completed project cost. The Ripple Down Rule (Ridor) classification algorithm was used to generate a set of rules from the database of bidding ratios that provides a prediction of the expected level of cost increase over the initial low bid price. The classification rules generated by the Ridor algorithm are presented. A test set was used to determine the usefulness of the generated rules in predicting project cost increases and results of the testing are presented.
Using Classification Rules to Develop a Predictive Indicator of Project Cost Overrun Potential from Bidding Data
Williams, T. P. (author)
International Workshop on Computing in Civil Engineering 2007 ; 2007 ; Pittsburgh, Pennsylvania, United States
2007-07-23
Conference paper
Electronic Resource
English
| British Library Conference Proceedings | 2007
Predicting project cost overrun levels in bidding stage using ensemble learning
| DOAJ | 2020
Predicting project cost overrun levels in bidding stage using ensemble learning
| Taylor & Francis Verlag | 2020
Factors Leading to Cost Overrun and Time Overrun in Pune Metro Project
| Springer Verlag | 2023