Applied Statistics Powers Success in Healthcare Finance

Paul Chwiecko ’02 found his perfect college match at RIT during a visit. “When I toured, it just felt like a good fit! The strong STEM programs caught my attention, and I knew this was where I wanted to be,” he says. Paul initially considered studying applied mathematics, but a pivotal moment in an algebra class helped him decide the career path he would follow.

“I remember in Linear Algebra, we derived the formula for ordinary least squares regression without using calculus, and that fascinated me!” Paul shares. “That class inspired me to switch my major to applied statistics.”

Today, Paul brings that same passion for applied statistics to his role as Manager of Finance for Government Programs at Excellus BlueCross BlueShield (BCBS), where he manages complex financial processes and data-driven decision-making. He tends to wear a few different “hats” depending on the time of year, but central to his core responsibilities are regression analysis for forecasting and statistical testing for outcomes measurement, including confidence intervals, t-tests, and ANOVA. He applies advanced multivariate techniques like Singular Value Decomposition and Principal Component Analysis to uncover patterns in complex datasets, along with methods such as Cluster Analysis, Segmentation, and Discriminant Analysis. These tools inform key business decisions, including how the company structures its products and identifies strategic investments through positioning and predictive modeling.

Through this work, Paul continues to apply the foundational skills he developed at RIT, including running regressions, scripting in SAS, and understanding statistical methods that were pivotal in shaping his expertise. “Regression analysis, ANOVA, Confidence Intervals, t-tests, and Design of Experiments measurement were all skills I learned at RIT and are tools I still use frequently,” he shares. While at RIT, Paul completed a co-op at Wegmans, a regional supermarket. There he learned essential technical skills such as SQL extracting and manipulating data, constructing Pivot tables, and building VBA macros in Excel. These industry experiences gave him early insight into applying data analytics to solve real-world problems.

When asked to describe his role today to someone outside the finance industry, Paul explains, “I try to help my company save money to keep costs affordable for members in alignment with the company mission, while at the same time looking for ways to help members maintain and achieve good health outcomes.”

Paul credits influential RIT professors in helping to shape his career, including Dr. James Marengo, who fostered an environment focused on mastering challenging concepts; Dr. Carol Marchetti, whose enthusiasm for statistical methods and invaluable guidance left a lasting impression; and Emeritus Professor James Halavin, described by Paul as “eccentric and fun,” who inspired him during an independent study in multivariate statistics and profoundly influenced his approach to solving real-world business problems.

Reflecting on his time at RIT, Paul encourages students to embrace opportunities to learn both in and out of the classroom. He offers practical advice for aspiring statisticians: “Learn SQL! It's been around forever for good reasons. Understand data extraction from Star Schema databases because most statistical techniques require flat, non-normalized data (in the database sense, not the statistical sense). Learn how to construct appropriate data structures to answer business questions, which is sometimes easier said than done. Also, learn how to script and master 1-2 programming languages.”

Beyond technical skills, Paul emphasizes the importance of communication. “Learn how to convey complex math concepts and insights to business-minded folks. You’ll need to help them understand the value these techniques bring in driving results and impacting decisions,” he advises. These soft skills, along with a strong technical foundation, are qualities he looks for when hiring new team members, ensuring they can bridge the gap between data science and business strategy.