Machine Learning Framework for Bundled Contracts Improves Efficiency and Cost Reduction

A recent study from the New Jersey Institute of Technology has developed a competitive bidding framework to help contractors prepare for bundled contracts in transportation infrastructure. The framework involves machine-learning models that predict the level of competition on bundled contracts based on input variables such as contract characteristics. This research has provided unique quantitative insights into the interplay between contract characteristics, competition, and profit when deciding on markup values for bundled contracts. Industry practitioners have deemed the framework both theoretically sound and practically viable.

Key Takeaways:

• The study developed a competitive bidding framework to assist contractors in preparing for bundled contracts in transportation infrastructure.
• The framework utilizes machine-learning models to predict the level of competition on bundled contracts based on input variables such as contract characteristics.
• The researchers analyzed a dataset of 1,650 bundled projects to develop and compare the performance of various machine-learning models.
• The study found that the characteristics of bundled contracts, expected competition, probability of winning, and expected profit are interconnected when deciding on markup values for bundled contracts.
• Industry practitioners have confirmed the practical viability of the framework, highlighting its potential to improve pricing strategies and bidding tactics for contractors.
• The study also revealed that public agencies can structure more competitive bundled contracts based on the expected level of competition.
• The developed framework can be used to predict the winning probability and expected profit for different markup values, enabling contractors to make informed decisions.

Statistics:

• The study analyzed a dataset of 1,650 bundled projects.
• The researchers developed and compared the performance of various machine-learning models to predict the level of competition on bundled contracts.
• The study found that the characteristics of bundled contracts, expected competition, probability of winning, and expected profit are interconnected when deciding on markup values for bundled contracts.
• The developed framework can be used to predict the winning probability and expected profit for different markup values, with industry practitioners confirming its practical viability.

Sources:

• "Predicting the Level of Competition and Determining Optimal Bidding Strategies for Bundled Projects: Integrating Machine-learning Algorithms and Probabilistic Modeling." Journal of Construction Engineering and Management, 2025;151(11).
• New Jersey Institute of Technology. Construct & Civil Infrastructure, Newark, NJ 07102, United States.