Using Machine Learning to Predict the Success of Architecture and Engineering Proposals

Architecture and Engineering firms bid on proposals worth billions of dollars per year with the goal of being awarded projects to generate revenue for the firm. The selection of projects to pursue requires strategic planning and resource allocation by management teams to identify which projects provide the best value for the firm. Improving the decision-making process to identify the projects most likely to be awarded to the firm is a means to improve the resource allocation process and reduce costs associated with preparing bid proposals. Preparing bid proposals requires teams to evaluate solicitations, develop plans, and draft responses which require human capital and time. Using machine learning as a predictive algorithm can improve this process and target the projects most appropriate to the organization based on past historical successes. This praxis develops a machine learning method to support management with the decision-making process by predicting which proposals to target for project selection. Improving the failure rate or non-selection of bids within project selection directly impacts the organization's revenue growth and limits wasted resource allocations to solicitations that will most likely not be awarded.

Author

• Howard Jr, Paul Raymond

Language

• en

Keyword

• Machine Learning
• Decision Tree
• Project Selection
• Artificial Neural Networks
• AdaBoost

Date created

• 2023

Type of Work

• Dissertation

License

• All rights reserved

Rights statement

• In Copyright

GW Unit

• Engineering Management

Degree

• D.Engr.

Advisor

• Campos-Nanez, Enrique

Committee Member(s)

• Campos-Nanez, Enrique
• Blackford, Jospeh P
• Etemadi, Amir

Persistent URL

•  https://scholarspace.library.gwu.edu/etd/9880vr66n