Northeastern University - Seattle
Ste. 103, 401 Terry Ave N
Seattle, WA 98109
Attn: Everaldo Aguiar, 109 SEA
401 Terry Ave N, Ste. 103
Seattle, WA 98109
- PhD in Computer Science, University of Notre Dame
- MSCS, University of Notre Dame
- BSCS, Midwestern State University, Texas
Everaldo Aguiar is a Part-Time Lecturer at the Khoury College of Computer Sciences at Northeastern University’s Seattle campus. He received his PhD from the University of Notre Dame, where he was affiliated with the Interdisciplinary Center for Network Science & Applications. His PhD research focused on the development, deployment and evaluation of machine learning models to detect, ahead of time, students that may be at risk of underachieving their academic goals. He was a fellow at the Eric & Wendy Schmidt Data Science for Social Good Fellowship, and a visiting researcher at the Center for Data Science and Public Policy at the University of Chicago, where through a variety of partnerships with large school districts, he was able to incorporate his predictive models to early warning systems that continuously monitor hundreds of thousands of students, informing educators when individual attention to a particular student may be needed.
He now works as a Data Scientist at Concur Technologies, where his research work is being leveraged and applied to highly complex and extremely large datasets. Some of his recent projects involved the development of predictive models that extract important token values from receipt images, and lightweight machine learning approaches to matching receipt images to their corresponding credit card feeds in real time.
What are your research interests?
In graduate school, my initial research focus was in the area of Computer Security, where I spent sometime investigating potential threats to new cloud computing paradigms as well as protocols for secure multiparty computation.
I later moved on to what became my main research focus, the field of Learning Analytics. I have multiple conference and journal publications pertaining to work that involved the application of advanced machine learning techniques to pressing issues in the field of education, both secondary and post-secondary.
What do you find most rewarding about what you teach?
Data Mining and Machine Learning techniques are very general and can be applied to any problem that produces or consumes data. Learning these techniques becomes extremely fun once students begin to identify interesting problems that can readily tackled by them. While industry professionals have been making use of these algorithms for a while now, because several easy-to-use implementations continue to be made available every day, anyone can now put machine learning to use on problems that personally excite them.
Where did you grow up or spend your most defining years?
I grew up in my hometown of João Pessoa, on the east coast of Brazil, where I also attended high school and began my college career. An opportunity came for me to complete my computer science degree in the United States and nearly 10 years later, and I am still here.
What are the specifics of your industry experience?
I now work as a Data Scientist at Concur Technologies, in Bellevue – WA. Concur provides travel and expense management solutions to dozens of thousands of clients world wide, and our data science team is responsible for various research projects that leverage the huge amount of data our costumers produce every second, converting that information into actionable products that enhance their experience.
Where did you study?
I was fortunate to meet my phenomenal undergraduate advisor (Dr. Nelson Passos) at Midwestern State University in Texas, and it was that connection (and the reasonable out-of-state tuition rates) that brought me to Texas. Following my undergraduate I immediately enrolled to the PhD program at the University of Notre Dame in Indiana, which was Prof. Passos’ Alma Mater. My first visit to Notre Dame’s beautiful campus was sufficient to convince me that I would like to spend my graduate school years there.