It’s complex. But not too complex. But I’m afraid that’s going to change soon.
We finished the data pre-processing section and feel pretty comfortable repeating it. Linear Regression was quite simple. # this probably can be done in Excel as well
We’re ready to move on.
The second step within Regression is Multiple Linear Regression. Code and math are hardly ever explained in detail, so sometimes it’s hard to follow without having to pause, reflect or google every once in a while. # things like p-value.. what was that again?
At this point, I feel like the methods, code and algorithms are pretty straight forward. For me, the interesting part comes with the dataset. In the MLR section we are looking at 50 startups, their location and their budget spent on R&D, admin and marketing. Is there a correlation between those factors and their profit?
Anticipating some sort of correlation, proving it and making further predictions with a few lines of code is quite intriguing. And this is only the beginning. I’m very curious about what’s to come next and can’t wait for our next session.