Abstract
Neural networks and regression models are employed to model the decision to bid process. The approach demonstrates the feasibility, and usability of the neural networks as a valid tool for modelling non-linear relationships. Moreover, neural networks provide a model with the desired accuracy for the decision to bid process. The paper recommends involving the end users throughout the system development process, and creating an environment within which direct and indirect learning can be achieved by practitioners.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the RICS Construction and Building Research Conference |
| Editors | R. Falconer |
| Place of Publication | United Kingdom |
| Publisher | Royal Institution of Chartered Surveyors |
| Pages | 331-339 |
| Number of pages | 9 |
| ISBN (Print) | 1-84219-027-X |
| Publication status | Published - 2000 |
| Event | RICS Construction and Building Research Conference 2000 - University of Greenwich, London, United Kingdom Duration: 30 Aug 2000 → 1 Sept 2000 |
Conference
| Conference | RICS Construction and Building Research Conference 2000 |
|---|---|
| Abbreviated title | COBRA 2000 |
| Country/Territory | United Kingdom |
| City | London |
| Period | 30/08/00 → 1/09/00 |
Keywords
- bidding
- decision support system
- construction
- neural networks