Asking the Right Questions: Alumni Spotlight on Suchandan Pal

Suchandan was a Fellow in our Fall 2016 cohort in San Francisco who landed a job at our hiring partner, Argyle Data – now Mavenir

Tell us about your background. How did it set you up to be a great Data Scientist?

I did my PhD in a part of mathematics known as number theory/arithmetic algebraic geometry. I’ve always been drawn to difficult and impactful problems, and my training has provided me with invaluable skills that I use use in problem solving everyday.

Knowing techniques and tools is important, but asking the right questions (and knowing which to avoid) is often what makes the difference between a problem you can solve, and one that remains intractable. For example, there have been many times where choosing the right strategy or perspective has made extremely difficult conjectures appear “natural” in number theory/arithmetic algebraic geometry. I have always found my experiences in mathematics to give me skills that guide me in problem solving outside of mathematics, and for that I am very appreciative.

What do you think you got out of The Data Incubator?

I enjoyed learning from Robert, the instructor of the San Francisco cohort. I also liked that Fellowship program gave me exposure to different sectors of industry.

What advice would you give to someone who is applying for The Data Incubator, particularly someone with your background?

I would say learn the Python library pandas well.

What is your favorite thing you learned at The Data Incubator?

I really enjoyed our first project. The input was a website that had lots of pictures, and each picture had a sentence underneath it indicating who was in the picture. Our goal was to answer some basic questions. For example, we had to determine which pairs of people are friends, who is the most popular, etc. We used Natural Language Processing to identify and extract names from captions, and basic graph-theoretic constructions and algorithms to answer the questions above.

Could you tell us about your Data Incubator Capstone project?

My goal was to determine if one can build an app that guides poorly performing taxi drivers so they can increase their hourly wage. One important decision that a taxi driver makes is the choice of where to go to look for customers. A naive strategy is to simply not move, and wait in the same general area until a customer arrives. Our algorithm determines where a taxi driver should search for customers by looking at the behavior of good drivers. It also factors in driving time with traffic and the cost of gas.

How did you come up with the idea for the project?

I’m passionate about empowering people to achieve the goals they set for themselves. One day, I was thinking about taxi drivers, and how I could help poorly performing taxi drivers make more money. How can such a driver increase their hourly wage without having a large network of colleagues to guide them with tips? I believed that one could use data science to solve this problem, and decided that the goal of my Capstone project would be to do this.

What technologies did you use and what skills did you learn at TDI that you applied to the project?

At The Data Incubator, I had access to experts in machine learning, and learned some excellent tools for data science, as well as new libraries for visualization of data.

What was your most surprising or interesting finding?

It was interesting to see the difference between drivers that follow a naive strategy, and drivers that follow the more informed strategy as dictated by our algorithm. Drivers that follow a naive strategy tend to make short trips to locations nearby. In comparison, drivers that follow the strategy suggested by our algorithm often have the audacity to make one or two trips without a customer in hopes of finding a more profitable one. It is initially somewhat counterintuitive that this difference increases their hourly wage by 10-12% on weekday mornings.

Describe the business application for this project (how could a company use your work or your data)

The goal of this project is to empower poorly performing taxi drivers to increase their hourly wage. Our algorithm can be used to tell a poorly performing taxi driver where they should go to search for customers in order to maximize their hourly wage. You can easily build smartphone apps to deliver these actionable insights directly to taxi drivers, and this could potentially have a lot of impact.

Do you have an interesting visualization to share?

And lastly, tell us about your new job!

I’m working as a Machine Learning Engineer at Apple, and my job is to use machine learning to help Apple improve its products. So far, I’m absolutely loving the experience.

Learn more about our offerings:

Related Blog Posts


Career Enablement at TDI

TDI is more than your typical bootcamp. We provide robust career support to ensure exceptional outcomes for our students. Learn more about our career enablement options here!

Read More »
is it too late to become a data scientist

Is It Too Late for Me to Become a Data Scientist?

You might think data science is a young person’s game. After all, this is a relatively new discipline that might not have been around when you were in school. But research shows nearly half of all data scientists are 40 years and older. Whatever your age, it’s never too late to pursue your dreams of becoming a qualified data scientist. Learn how to succeed in this profession in this blog.

Read More »