| INDUSTRY
CONSTRUCTION |
AI SERVICE
MACHINE LEARNING, DATA-DRIVEN PROJECT STRATEGY |
Predicting Which Prospective Construction Projects Would Be Profitable
We built a predictive model to help a market-leading construction company better utilize their data to assess the profitability of prospective projects.
Problem:
For several decades, our client–one of the largest, most diversified construction companies in the United States–relied on its highly experienced project managers to identify and map project risks to profitability. This project-related data was collected in various disconnected systems. But these experienced project managers’ collective “know-how '' was never assembled or codified for future projects to use to assess risk. The firm was concerned that as these experienced project managers retired the firm’s ability to assess and mitigate project risk would wane dramatically affecting their profits and client satisfaction. The CIO and Project Management team identified an opportunity to apply innovative technology to address this future problem.
What can you learn from AI-powered data-strategy solutions in construction?
Manual approaches to assess project profitability risk are difficult to maintain resulting in lost revenue, dissatisfied clients, and an over-dependency on project managers’ experience. However, when collective knowledge is captured and provided to project managers as a risk assessment tool, it continues to add value and increase returns.
Beyond the data-rich construction industry, predictive learning models like the one we built for this construction firm hold incredible promise for many other fields including legal and manufacturing.
Let us help you improve the quality of your data →Solution:
We began the engagement by interviewing the firm’s experienced project managers to establish a baseline of understanding regarding project risk projections. We learned that the project managers had formed rules to identify project risks. These risks, called “leading indicators,” essentially project milestones related to anticipated delays, help to predict project risk and associated losses or cost to the company.
Collectively, the project managers articulated five leading indicators of profitability for the company’s projects overall. We used these indicators to create a model based on past project data. The model revealed the most promising leading indicators and helped validate assumptions made by project managers. When diving into past project data, we discovered that tasks and overall budget were tracked in separate tables. We needed a bridge table to connect the data, which led to a substantial data engineering effort.
We helped the CIO and Project Manager’s team join data rows from all the separate tables. Once we obtained connected data, we performed statistical analysis to understand the distribution of values for each key field and how many had null or erroneous values. We used this information to clean the data in preparation for building a predictive model.
In addition to building the foundations for the model, we also learned that the leading indicators’ names were entered into project plans using different variations per project. This afforded us another opportunity for improvement by unifying these variations into canonical names for downstream processing.
We built a machine learning model to predict project profitability from the values in the leading indicators, i.e., delays in key project milestones. A key element was finding the right profitability threshold to define what profits are acceptable and unacceptable.
Outcome:
We worked with the CIO and Project Management team to incorporate domain knowledge into visualizations of past profits. The final result was a classifier that predicted whether project profit would be “acceptable” or “unacceptable” with 86% accuracy.
At least 1,000 new employees can take advantage of the knowledge from experienced project managers to increase ROI per project.
HUMANKIND OF IMPACT
AI IS HOW WE DO IT,