Skip to main content
Log in

A machine-learning-based framework for contractor selection and order allocation in public construction projects considering sustainability, risk, and safety

  • Original Research
  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

Effective contractor selection is crucial for successful execution of construction projects. In contrast to the conventional lowest-bid approach prevalent in the public sector, this study focuses on developing a framework that minimizes time and cost overruns by considering diverse criteria for contractor selection. A variety of machine learning models, including multi-linear regression, random forest, Support Vector Machine, and Artificial Neural Network, have been employed, with multi-linear regression proving to be the most effective, achieving the lowest Mean Squared Error of 0.00003366. To determine the final order allocation, a multi-objective mathematical model was utilized to optimize conflicting criteria, such as time and cost overruns, sustainability, risk, and safety aspects related to shortlisted contractors. The findings highlight the significance of specific selection criteria, such as turnover, experience in similar projects, qualification of staff, technology utilization, client satisfaction, accident records, available bid capacity, and socioeconomic factors. This study emphasizes a three-phase decision-making framework for contractor selection and order allocation, particularly in public construction projects, with a focus on sustainability. By adopting this approach, government agencies can enhance infrastructure projects and minimize overruns through optimization and analytical tools, which aligns with the Gati-Shakti scheme of the Indian government. It is recommended that clients embrace a holistic approach to contractor selection, considering both technical and non-technical factors, to ensure successful project outcomes.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability statement

The data supporting this study’s findings are available upon request from the corresponding author.

Abbreviations

AHP:

Analytic hierarchy process

AI:

Artificial intelligence

ANN:

Artificial neural networks

ANP:

Analytical network process

CO:

Cost overrun

CO2 :

Corbon

CSR:

Corporate social responsibility

3D:

Three dimensional

DPR:

Detailed project reports

DEA:

Data envelopment analysis

GP:

Goal programming

EPC:

Engineering, procurement and construction

ISO:

International Organization for Standardization

LP:

Linear programming

ML:

Machine learning

MSE:

Mean squared error

MCDM:

Multi-criteria decision making

PROMETHEE:

Preference ranking organization method for enrichment evaluation

SC:

Subcontractors

SVM:

Support vector machine

RMSE:

Root mean square error

TOPSIS:

Technique for order performance by similarity to ideal solution

TO:

Time overrun

WSM:

Weighted sum method

References

Download references

Acknowledgements

The authors have not received any funds for this research work and totally depend upon themselves to carry out this study.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sunil Kumar Jauhar.

Ethics declarations

Conflicts of interest

The authors have no conflicts of interest to declare.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix

A brief description of the input and output factors used in our study.

Input factors

This section provides information on the inputs used in our research.

2.1 Financial capability

This analyzes the financial situation and gauges the stability of a contractor's finances in several contexts, such as bank accounts, bank support, accessible credit, assets, and profit from projects.

  • Credit rating The CRISIL credit rating of a firm is used to determine its creditworthiness.

  • Turnover capacity How much money can the business make in a year compared to the minimum requirement set by the owner?

2.2 Technical and management capability

This criterion considers a company's technological expertise as well as that of other staff members. The experiences were further separated into two types: generic and unique to a given project. Past performance is closely related to experience and indicates past successes, unpleasant past experiences, and the history of successful ventures.

  • Experience in similar projects Number of years working on similar types of projects. This factor is more important than the experience.

  • Qualification and experience of staff This refers to a company's technical staff. Clients in this situation are interested in the size and expertise of human resources such as engineers, associate engineers, and other critical employees. This assesses the contractor's managerial skills with regard to office and site management. This is demonstrated by the qualifications and expertise of all essential personnel including the project manager. Furthermore, it covers the firm's general project management, as well as planning, scheduling, monitoring, and control procedures.

  • Technology being used by the bidder Additionally, the bidder's analytical skills may be considered (as per GATI SHAKTI). This demonstrates the effectiveness of a contractor in terms of using cutting-edge technology, such as the use of sophisticated tools for planning and monitoring the job, and further utilizing cutting-edge tools and equipment together with contemporary construction techniques. Equipment capability is reflected by the availability of tools and machinery. Additionally, this category includes the sufficiency and compatibility of the equipment. Individual departments were asked to rate the contractors based on the software and technologies used in their respective domains. The average of all values was calculated. Eg. Naviswork, STAAD Pro, AutoCAD, Primavera P6, MS Project, use of UAVs, IoT-enabled devices for monitoring, Building Information modelling.

2.3 Reputation

Reputation is measured using past accolades, customer and consultant satisfaction, and reputation. The types of complicated projects that have been successfully completed in the past are covered by certificates of recognition, which can be used to measure this criterion further and are provided by various bodies.

  • Record of past failures A number of projects of similar nature were not successfully completed by the contractor. This is rated on the basis of abandoned projects; that is, they have letters of intent/work order but do not have work completion certificates.

  • Client satisfaction rating This is a way to gauge customer satisfaction by considering a contractor's previous interactions with customers, consultants, current customers and consultants, suppliers, subcontractors, banks, funding organizations, insurance companies, and so on. This is gauged by the work completion certificate issued by other clients to the contractor.

2.4 Quality

This measures the extent to which the contractor is capable of delivering high-quality results. Here, a number of factors are examined, such as how the contractor monitors and controls quality and the related mechanisms and rules. Customers can measure this parameter with the aid of endorsements such as ISO certification.

Adherence to specification Previous similar work qualities: This is gauged from various ISO certifications and work-completion certificate data.

2.5 Technical and commercial bid

The suitability of the contractor for managing and completing the current project was assessed by commercial and technical bid groups. This group includes the bid to estimate the ratio, adherence to schedule metrics, and available bud capacity.

  • Bid to estimate ratio This variable represents the ratio of the contractor's bid to the estimated project value. Any value less than 0.8 is a red flag for the project

  • Available bid capacity The amount of construction work that the department believes a specific contractor is capable of successfully completing a specific period is referred to as the bidder's capacity.

2.6 Health and labour well-being

The contractor's approach to the project's health, safety, and environmental considerations is demonstrated by the safety parameters. This is further supported by the availability of pertinent personnel, policies, and accident history.

Injury, illness, and accidents The firm follows safety standards. Previous records of worker injuries or illnesses. This is a quantitative measure based on the number of accidents that occurred during past projects undertaken by the contractor.

2.7 Environmental

The environmental organization addresses the contractor's actions at the job site that have an impact on the environment. Environmental management includes strategies to lower energy consumption and reduce emissions into the system (Zou & Moon, 2014). On a building site, energy management strives to control and manage every form of energy. The amount of energy required is reduced by using more energy-efficient equipment and removing the large and superfluous equipment.

Environmental management This metric considers the environmental management practices that the organization uses for its projects. This includes using practices that reduce harm to the environment, such as the proper usage of resources without harming the environment. This is a qualitative measure that is assessed using ISO certifications that the contractor has like “ISO 14001 (Environmental Management System).” “

2.8 Socio-economic

From an economic and social standpoint, the socioeconomic group examines sustainability. Local resources, social and business responsibilities, and environmentally friendly purchasing were all included. CSR demonstrates how committed a corporation is to sustainability and community service. This dedication is demonstrated through a variety of actions, such as activities that raise public awareness of the value of such sustainable projects and the benefits they provide for both our planet and way of life. Utilizing local resources encourages self-sufficiency within the nation and lessens the carbon footprint created by transportation corporations in order to provide what is required. This entails hiring local laborers and employees and using building supplies that are readily available in the area rather than relying on imports or placing orders from afar. If conducted on a broad scale, this would assist in strengthening the local economy by creating more jobs nearby. This has a positive impact on society, the economy, and the organization as a whole, while causing the least amount of environmental harm.

Use of local resources This indicator indicates the extent to which the contractor uses local resources during a building project. Utilizing local resources encourages self-sufficiency within the nation and lessens the carbon footprint created by transportation corporations in order to provide what is required. This entails hiring local laborers and employees and using building supplies that are readily available in the area rather than relying on imports or placing orders from afar. If conducted on a broad scale, this would assist in strengthening the local economy by creating more jobs nearby. CSR demonstrates how committed a corporation is to sustainability and community service. This dedication is demonstrated through a variety of actions, such as campaigns that highlight the significance of such sustainable projects and the advantages of their implementation for both our planet and our way of life. It is gauged by the percentage of local resources used by contractors from India.

Output factors

This section provides the details of the output factors that are going to be utilized for our research.

3.1 Time overrun

"A condition when a construction project is not completed within the designed schedule" is the definition of time overrun. The causes of construction project delays vary.

3.2 Cost overrun

This is a phenomenon in which the client or contractor ends up spending more money than originally anticipated to complete the job. For example, a project could exceed its budget.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jain, S., Jauhar, S.K. & Piyush A machine-learning-based framework for contractor selection and order allocation in public construction projects considering sustainability, risk, and safety. Ann Oper Res 338, 225–267 (2024). https://doi.org/10.1007/s10479-024-05898-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10479-024-05898-6

Keywords