Large Data S-curves for Construction Project Estimation and Comparative Analysis


Details
This presentation explores S-Curves; an analytic technique for project planning and estimation. At Trimble, we use S-Curves to help construction companies pragmatically estimate and compare their construction projects. Our work extends the traditional S-Curves techniques developed by A.P. Kaka et.al with big data and simulation techniques. Since our construction project databases are too big to be processed on a single CPU or even multi-CPU computer, we will discuss how we use high-performance compute clusters (Apache Spark and Databricks) to perform our calculations.
Topics Covered: Nonlinear Logit transformations, linear regression (and associated optimization and statistical analysis), simulation, and cloud processing (AWS and Azure). It will be all about how we can use AI and have fun while we do it!
About the presenter: Miles Porter - https://www.linkedin.com/in/milesrporter/
Miles is an experienced data scientist focused on image processing, time series analysis, and combinatorial optimization opportunities.

Large Data S-curves for Construction Project Estimation and Comparative Analysis