Developing an Efficient Ensemble Machine Learning Model for Generating Insights and Evaluating Contractors Qualifications for Successful Execution of a Construction Project

The research is meant to invent a quicker and efficient method for evaluating potential suppliers for public sector procurement, especially for construction services. This is a complex and paper intensive process today. Using machine learning models to decipher data and
PledgX is focused on building a solution that enables public sector buyers evaluate suppliers more efficiently and quickly using AI-driven insights. These insights are generated from data collected from suppliers at the stage of submission.
By analyzing data that is available in pdf/excel/word files in the company’s records, PledgX is building an easy-to-use tool to guide GCs to build a prequalification package. This process also ensures that data is collected from GCs more efficiently at this stage in comparison to the paper/pdf/word/excel documents submitted today.

Faculty Supervisor:

Rasha Kashef

Student:

Partner:

PledgX

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Toronto Metropolitan University

Program: