Armand was a Fellow in our Fall 2016 cohort who landed a job with KPMG.
Tell us about your background. How did it set you up to be a great Data Scientist?
I received my Bachelor’s degree in Mechanical Engineering from NC State University. After college, I became a management consultant specializing in program and strategic management. As a consultant, I saw the value of data-driven decisions and extracting insights from data. As a result, I decided to go back to school to obtain my Master’s in Systems Engineering. There I was introduce to R Programming software, data mining techniques, and applications of optimization. My Masters not only exposed me to data science, but it also provided me a framework to approach complex problems.
What do you think you got out of The Data Incubator?
What advice would you give to someone who is applying for The Data Incubator, particularly someone with your background?
The Data Incubator provides a bridge to transition into a career in data science. For those applying who have a similar background as I, begin to identify how you can transform your current projects to take a more data science approach and implement those ideas if you can. If you are accepted, utilize the 12-day preparation course as it provides a lot of information, and if you are like me a lot of it will be new to you.
What is your favorite thing you learned at The Data Incubator?
Although I could name a number of favorite things I’ve learned, to be brief I will share only my favorite concept and my favorite interview prep. My favorite concept was MapReduce and distributed computing. I found the concept interesting because it provides a way to manage data that is too large to store in local memory. My favorite interview prep was the daily coding challenges. These challenges expose me to several algorithms and data structures that I had no prior experience with. It also forced me to take into consideration the time and space complexities of my algorithms. These were all topics focused on during my technical interviews.
Could you tell us about your Data Incubator Capstone project?
The inspiration for my capstone was rooted in my upbringing. I was born and raised in North Carolina and went to school at North Carolina State University, which is located on “Tobacco Road” – The Heart of College Basketball. That is why I chose to explore college basketball game data and I used it to develop and upset classifier. My app presented insights on Division I Men’s College Basketball games as it related to identifying upsets throughout the college basketball season. I built a support vector machine classifier, which was trained using the previous three season, accounting for over 17,000 data points. I provided three modules for the user. The first module provided the probability of an upset for each scheduled game. The second module provided the correlation between game statistics and the upset probability. The third module showed the models performance on predicting NCAA Tournaments.