Joe Chen
By Joe Chen, Data Analyst Intern
August 5, 2019
As I reflect on my last day as a summer intern, I want to emphasize how grateful I feel for the opportunity to work as a Data Analyst Intern for the Division of Maintenance and Operations. My time here has given me invaluable experience with cleaning, summarizing, and visualizing big data sets.
I loved working with highway pavement data because I got to apply my training from school while also independently learning new data techniques to meet challenges I have not been exposed to before. In school, professors usually provided me with data that was already clean and ready to be analyzed. However, I discovered that the raw highway pavement data I worked with at the Colorado Department of Transportation (CDOT) needed lots of cleaning before it could be analyzed.
Photo of Joe Chen (left) and his CDOT mentor (right)
I learned firsthand 80% of a data scientist’s time is spent cleaning the data. However, after I cleaned it up, I was able to start analyzing and visualizing the highway pavement conditions using R and R Studio, a software and language for data analysis.
Before I came here, CDOT had all this pavement data collected every year but it was not being used. The short-term impact of my work helped our division start to track how effective certain pavement treatments are. For example, if we did a chip seal treatment in 2016 on a highway, how long will this treatment last until the conditions are bad again? Which conditions get better and which get worse? Now that I have helped show the value of using the pavement data, the long-term impact would be CDOT moving towards using the pavement data to decide where to pave and what treatments are the most effective.
None of this would have been possible without the support and kindness of my two bosses, Scott and Tyler! I am excited to take what I have learned back to Emory University where I will start my final year studying Quantitative Sciences!
Contact: joechenco@gmail.com