Machine learning is a little bit like yoga: we all know what it is, we all know it’s good for us, but few of us understand how to actually do it. There’s a mystery surrounding machine learning that (even if our colleagues won’t admit) leaves many people in the built environment overwhelmed. Still, machine learning is more than just an industry buzzword at this point; it’s a necessity.
We’re way past the point of buzzword with artificial intelligence in engineering and construction. It’s no longer just an idea, but a make-or-break business reality.
In the previous article we gave you an introduction to machine learning in construction, and we mentioned that machine learning can be broken into two broad categories: supervised learning and unsupervised learning. While supervised learning has an output or response variable that analysts are focused on (for example, a cost performance metric), unsupervised learning relies on having no response variable – the objective is to simply explore the data available.
