Hands-On Supply Chain with Machine Learning

I recently finished the third course in MIT’s Supply Chain MicroMasters program, Supply Chain Design, hosted on their EdX platform. I scored an 86% on the final exam with an overall grade of ‘B’ for the class (which I expect will end up being average). Considering time constraints with work (especially working in supply chain in retail during peak) and family… I felt pretty good about this performance. In general, though, I’ve always been (or I’ve always seen myself as) a strong ‘B’ student. Knowing this, I’ve realized that if I want to be great at what I do, I need to be a strong ‘B’ student in lots of different things and bring those all together.

That means taking some supply chain courses and reading supply chain detective novels, alone, won’t get me where I want to be. I love data science and machine learning. I spend lots of hours taking classes (Udacity), doing tutorials (Kaggle competitions), and reading subject-related content as much as possible. I don’t work in the space directly, so to become that strong ‘B’ student I need to find other ways to practice deliberately and improve. I wrote a kernel on Kaggle which replicates a chapter from Hands-On Machine Learning with Scikit-Learn and Tensor Flow using an alternative dataset (2015 US Traffic). By doing all of this, my hope is that when I get to work with the data science, machine learning, and supply chain ‘A’ students, I can at least understand most of what they talk about and help generate new ideas for applying data science and machine learning to supply chain problems.

https://www.kaggle.com/frankcorrigan/end-to-end-data-science-project

Leave a Reply

Your email address will not be published.