My love for analyzing and finding patterns in the world around me started at a young age; I’ve been told when I was five my mother found me arranging all the sweetgum tree balls in our North Carolina yard from smallest to largest. I was able to apply these natural tendencies to more consequential problems during my undergraduate work at Bucknell University, where I earned a BS in Chemistry. My honors thesis at Bucknell was my first foray into applied data analytics when I developed and published a method of analyzing Atomic Force Microscopy that allowed for the observation of swelling dynamics of smectite tactoids at a nanoscale level. The key to this research was to perceive the images as matrices of XYZ data points that are categorized by individual z-planes to isolate inter-layer absorption behavior. (Find the published work here.)

A Shift in Perception

I was intrigued by this idea that a shift in perception could alter the data analytics to successfully solve a problem. After college, I spent two years in the Peace Corps teaching French at a secondary school in Mozambique, where Portuguese is the official language. Immersed in a new culture and way of life, to solve my student’s problems I turned to collaborating with my Mozambican counterparts to come up with effective solutions. My mind was further opened to the advantage of suspending pre-conceived ideas and embracing the expertise of those around me to more clearly discern a resolution.

I then obtained my master’s degree in Chemical Sciences from the University of Pennsylvania. Applying some of the open-mindedness I adopted during my time in Africa, I continued my research in data analytics, this time coding an application to calculate the quantity and size of nanoparticles in Transmission Electron Microscope images. Instead of segregating particles from the image background using the standard plane method, I developed algorithms to plot the perimeter of each particle by solving differential profiles radiating from the center of the particle. This new way to look at the images allowed me to identify perimeters based on data local to each particle within the image rather than relying on average data across the entire image. In addition, the new method had the benefit of helping to mitigate black-box process bias by introducing confidence intervals that allowed the user to remove “blurry” particles that had a greater calculation error bar from average statistics.

Problem Solving From New Points of View

While completing my masters, I took a job working as a data analytics contractor in the financial services sector. At the time, I knew I was interested in data analytics but had little experience with financial services. My first year was a whirlwind of learning SQL at breakneck speed while trying to absorb the knowledge of the skilled programmers, analysts, and financial service experts I worked with. As I became more proficient, I realized that the satisfaction I felt in this job was similar to my previous experiences; it was founded on the thrill of collaborating with experts and the gratification of seeing the results of our efforts helping clients to solve problems. Forming Artemis Insights was the natural culmination of these experiences, allowing me to assemble a group of open-minded specialists eager to solve problems using our combined points of view. I started with a financial services division and immediately brought experts in the field onto my team. We value flexibility and adding new perspectives to the group; for new projects we take on, more experts are brought into the fray to ensure we have the ideal skills to take on any problem. While I’m still inclined to order sweetgum tree balls if they’re in front of me, I take greater pleasure in organizing our team and creating innovative products with our clients.