At logistics consulting firm St. Onge, data scientist Chase Mattingly '22 '23G automates processes, optimizes workflows, and analyzes data for the company and its clients. The computer science and engineering (CSE) alum is also one of the first students to graduate from Lehigh's MS in Data Science program. Today, he's leveraging the advanced skills learned in grad school—including big data analytics, optimization for machine learning, and statistical modeling—to make an impact in the fast-paced supply chain industry.
Q: How do you define the concept of data science?
A: In basic terms, I see it as an interdisciplinary field where the objective is to extract patterns found within sets of data.
Q: Describe the work you do as a data scientist in the supply chain sector.
A: In my first 100 days, I've worked on incorporating machine learning into supply chain optimization, fine-tuning large language models, web scraping, data cleaning, data synthesis, and developing web applications. We were able to automate the process of gathering important information, such as descriptions and dimensions of stock keeping units (SKUs), which previously required manual efforts. I was also able to leverage machine learning algorithms like clustering when creating a warehouse flow optimization web application. I am currently working on two products for the company, a data-cleaning web application that leverages complex data synthesis ML algorithms and data-cleaning procedures to automate the process for the engineers, plus a large language model (LLM) with retrieval augmented generation (RAG) fine-tuned on company documents for internal use.
Q: What skills that you developed as a graduate student are you applying in your role?
A: I took a few courses in big data analytics where I learned techniques to handle and process large volumes of data, which is crucial in supply chain. I also took optimization for machine learning, where I learned valuable methods that can be applied to data analysis to improve resource allocation. I am now looking at using GPUs and CUDA to compute tasks in parallel and handle large-scale data more efficiently, many techniques I learned from the Accelerated Computing for Deep Learning course.
Q: Why did you choose to go to grad school for data science?
A: Many job positions in machine learning require a higher level of education. I finished undergrad early and I was also interested in a research project with Professor [Eric] Baumer in the CSE department related to natural language processing. I opted to stay another year at Lehigh and get a master's in data science because it aligned better with my specialization in machine learning and offered new courses that I hadn't taken before.
Q: Are there any specific experiences from Lehigh's program that you felt were especially helpful or meaningful?
A: My research experience and thesis, for sure. Discussing my research during job interviews really showcased my expertise in the field. Working on research papers and publishing them allowed me to apply my knowledge in practical settings. Collaborating with PhD students and professors helped expand my knowledge, and reading and implementing methods from research papers has been valuable in my current role. When I started, I wasn't familiar with the supply chain sector, but I was well-versed in machine learning methods and how they are used in other fields, so I've been able to connect the two and use that knowledge in this industry.
Q: What would you tell an undergraduate student who is considering Lehigh's MS in Data Science program?
A: It was a great experience and I am glad that I chose it. I learned a lot and the hands-on research experience has helped me tremendously in my career. Class sizes are small and you get a good mixture of applied and theory-based courses. The professors are amazing and always there to help.
—Interview by Alyssa Caroselli '24, a student writer for the P.C. Rossin College of Engineering and Applied Science
