After graduating with a bachelor’s degree in chemical engineering, Melanie Hanna worked in a variety of manufacturing settings, including a polyurethane plant. But lacing up steel-toed boots every morning was not the life for her.

When given the opportunity to work for a large pharmaceutical company in their pilot plant—an offer most chemical engineers would jump at—Melanie realized she had zero excitement to do the job and decided she needed to pivot.

Drawn toward analytical thinking, Melanie ultimately decided that she wanted to pursue data science. Studying chemical engineering in school gave her a base in data science concepts, but Melanie knew she needed further education. What she didn’t know was which program suited her needs.  

After thorough research, Melanie chose Springboard’s Data Science Career Track. Most programs she came across were in-person or too expensive. But Springboard allowed her to continue working full-time and offered one-on-one mentorship. And, she said, “the job guarantee made Springboard a no-brainer.”

Melanie HannaBy far Melanie’s favorite part of the Springboard experience was completing the capstone projects, which gave her the chance, she said, “to apply the skills we were learning toward projects I was passionate about.”

A (nearly) lifelong Chicagoan, Melanie picked a topic close to home for her first capstone project: predicting pothole frequency in the city, along with the Department of Transportation’s response time.

It seemed to Melanie that there were more potholes in certain areas of the city. To test that idea, and to determine whether any specific factor, such as income, correlated to pothole creation or city response time, she turned to the data.

To traverse the data set, Melanie worked in Python, primarily using the scikit-learn and pandas packages. She utilized a random forest model to ultimately determine that income was not an important predictor for pothole repair time.

For Melanie, the project reinforced the idea that she learned the most from actually digging into data. She also discovered how challenging working with a data set can be. There are so many possible avenues to go down while looking for trends or correlations that it can be easy to get lost. The key is recognizing when you’ve learned everything you can and should move on to the next part of the data science process.

Armed with capstone projects that showed off the skills she mastered during Springboard’s Data Science Career Track course, Melanie landed a job as a data scientist at Arity, Allstate’s predictive-analytics startup. Melanie said she’s excited to work with a team to create pricing models for the insurance industry based on telematics data.

In her new role, Melanie works on “productionalizing” models and turning model results into repeatable calculations that can be used throughout the company. She spends most of her day programming, meeting with business stakeholders, and working with data engineers and developers to ensure an error-free pipeline of data and transformations.

When asked what advice she would give to someone interested in transitioning to a career in data science, Melanie said: “Start building models, either through Kaggle competitions or on your own.”

She added, “I’d absolutely recommend the Data Science Career Track. With the job guarantee, you just can’t lose.”