There are many perspectives on what data science is about from many blogs so I'm not going to prescribe any conceptual frameworks in this one. Instead, I will choose an evidence/experiential approach that is, I will show you what I did on a daily basis as a data scientist. What I need to do to keep up with this fast evolving field. I will demonstrate the skills I need to use on a daily basis as well as what I'm learning currently.
To be honest, I think there are a lot of fundamentals in data science not correctly applied because many practitioners focuses on the outcome of the prediction. I would try to tie the outcome with the fundamentals and show that fundamentals are very important not just conceptually or theoretically but it makes a big difference in terms of practical purposes. As a data scientist, I think my role is to digest the theory to the point that it becomes a living reality to the problems I'm solving using machine learning. Therefore, in this blog, I will also talk about some fundamentals that affect my work on a daily basis. For example, precision, recall, f1-score, p-value, credible interval, maximum likelihood, bayesian theorem, Empirical Bayes, statistical modelling, information theory just to name a few on top of my head. I want to show that you don't need to apply the most sophisticated algorithms to solve real world machine learning problems. You can add values to any machine learning projects by applying the fundamental in machine learning correctly.
The format of the blog would be based on solving real world problems using machine learning. There would be a specific problem statement, the reason why this is important, how can it be solved. Sometimes, I would show bugs that I found in machine learning libraries that I used and discussed them in length.
I hope this blog will be served as a discussion forum where we can share ideas as well. So feel free to comment. Enjoy!
