Hey. Sorry, I don't really get it.

Do you speak about Maths or Statistics? Both are seperate disciplines which surely are interconnected, but still should be handled differently.

As someone who is into Computer Science AND Data Science I must say that you NEED a fundamental knowledge about Statistics, its models, distributions, and so on. Otherwise, how do you interpret your results?

Sure, you can throw some numbers at your regression model and you will eventually get SOME results. But are they correct? Are those reliable? How do you interpret the numbers in your output (all of them and not only the R² and the fancy predicted values)? How to prevent over- or underfitting? Is Homo- or Heteroscedasticity something to keep in mind for your model? Can you adjust the model without doing p-hacking?

Additionally, fundamental understanding of Mathematics is important as well. You learn abstract thinking, complex problem solving, algorithms (yes, that's a field in Math and in CS) - basically all you need to write models that use your resources efficiently. Yes, you can use some preconfigured sorting algorithms but will you be able to tell which one uses the least resources for your use case?

Sure all of this takes time, but it comes with a good compensation. I mean, people in the data field are highly paid for a reason, right?

Taking the short route might get you on speed at the beginning. But chances are that you get stuck somewhere if you just use some predefined models in Python or R.

If you don't understand the basic concepts behind those, will you be able to question them if there's something wrong? Or maybe those models have some more capabilities or limitations you don't know. How will you get past that without understanding them?