Improving Construction Permitting Process using Predictive Analytics

In public sector, the decision making of construction permitting can have direct impacts on the ongoing urban development. The efficiency and predictability of the review process is critical for municipalities to provide timely and accurate results to the public. As the review process is managed digitally with process data available, using data analytics to develop predictive models can result in improvement of efficiency and predictability. Therefore, the City of Edmonton collaborates with the University of New Brunswick on a research project to utilize simulation techniques to provide predictive analytics to assist construction permit decision making. A Discrete Event Simulation (DES) will be used to represent the construction permit procedures virtually and incorporate historical and real-time data to predict the permit processing time. The developed simulation engine will be able to run what-if analysis to improve resource assignment in the permit review process, and eventually reduce the inefficiencies and bottlenecks. The develop simulation model will be integrated with the City of Edmonton’s existing operating system to provide timely decision support information for its construction permit review process.

Faculty Supervisor:

Zhen Lei

Student:

Jose Daniel Cuellar Lobo

Partner:

City of Edmonton

Discipline:

Engineering - civil

Sector:

Other

University:

University of New Brunswick