Aryash entered high school with a strong background in coding. He built on this through high school, taking a Java course at UC Berkeley as a rising sophomore and participating in an engineering program called BlueStamp where he worked on two image recognition projects. One of his projects was a smart mirror that would turn on based on the user’s facial expressions and emotions. 

That experience introduced him to the vast theoretical, practical and moral concerns associated with machine learning that he hoped to do his own research in. With QRI, he worked on affective computing, a subfield of machine learning involving facial recognition algorithms that can identify emotional indicators like smiles. Drawing on more than 40 research papers in the field, his paper compared the performance of three prominent machine learning models and analyzed important ethical considerations associated with affective computing.

When applying to Northeastern to study computer science, he listed his research project as one of his top activities on the Common App list. Research has the greatest impact on an application when it is presented as part of a narrative—by tying it to other activities that students have done before (or after). By establishing an academic “spike” in machine learning, Aryash set himself apart as an accomplished and high-potential computer scientist who would make effective use of Northeastern’s research opportunities and internship programs.