Might I do a gentle reminder here that "Machine Learning is not MAGIC!"
Like any other tool, it has its strengths and limitations. As a data scientist, we need to understand each machine learning model and how it separates the targets (rules, probabilities, separation boundaries, etc) or detects structure in training data.
What is a good starting point?
1) Understand the mathematics behind, how are the rules, coefficients, and boundaries derived.
2) Understand their strengths and also the underlying assumption of these models.
3) Understand also the limitation of these models, which usually have to be coupled with the training data to get better insights.
Despite what a lot of boot camp ads displayed (at least here in Singapore), data scientists do not perform magic! We SOLVE business challenges with data! Plus our jobs are really not glamorous as a magician! :)
I wish you all the best in your data learning journey and career!
What are your thoughts?
Consider supporting my work by buying me a "coffee" here. :)