Yingkun Huang

This project was an excellent experience for me, and it was quite challenging as for the first time, I got to work hands-on data with 70 million data records.

Working on an industry project was an excellent experience for me as part of my Master of Data Science. It was quite challenging as for the first time, I got to work hands-on with data to find insights and learn how to use that data for a business. This project was also my first time picking up the role of a project coordinator and managing the team was not something I had experience doing. It was through working with my industry supervisor that I realized my full responsibility as a coordinator: I had to make sure the fuel tank was full, and everybody was contributing.

A good industrial partner makes great impacts on our learning through the project and has really shaped my experience. One of the main things I learned during the project was during the data pre-processing stage. We tried to derive data fields we thought would be helpful in later stages to streamline our work but we found that it wasn’t until we had lived through this kind of experience, that we understood this kind of work.

We went back and forth in this stage as every data field has its reason to stay on the list. However, our supervisor guided us the right way to tangle the problem. His advice has stayed with me since and encouraged me to "think of what your outcomes are like, and then, thinking backwards to find the ‘minimum work needed’ path that can realize your goal." Learning to work efficiently to complete our task has been a major breakthrough for me to learn how to manage such large and complicated data sets.

The most valuable gains we took away from this project was the ability to find the proper tools we needed, learn a tool in a short time and put it into use. For our project we built the system from scratch, we needed to find appropriate tools to store, transfer and process our data-set and we needed to work with our industry partner to keep the project on track. We learned how to use Google Cloud Platform, Tableau, and Javascript to write webpages in this project. This ability to use, adapt and learn new skills, I believe, will help me in my career, especially in this open-source, fast-forwarding world.

Find out more: