Embedded Files
This page contains information about courses you might take that are outside of the Economics Department. Students may want to consider taking courses in other departments at Northeastern, or at other universities. This page lists courses other students have taken and includes their feedback.
The university limits the number of courses you can take for credit outside of the department, but auditing courses with the instructor's permission is also an option.
In general, economists find courses in mathematics, statistics, computer science (including machine learning), operations, finance, and other business fields useful for their teaching and research. However, keep in mind though that Northeastern does not offer PhD courses in finance or business - there are no PhD programs in the business school.
Course: Big Data Econometrics at Boston College
Student: Arvind Sharma
Comments: I audited the course in my first year at Northeastern University. The class was divided into two teams of about 5 people each, and we tried answering how to better engage the BC alumni online in an e-mail donation campaign to raise more funds.
We got to work with a few rich, proprietary datasets (~6GB). We learnt how get around lack of computing power using novel methods. It was primarily a project driven course with the course instructor introducing us to non-linear regression techniques, data management/workflow systems, troubleshooting common issues when handling large (>1 GB) datasets and demonstrating popular software used widely in the industry.
There are lots of online resources that one can find to build data science skills in general - I found the infographic at Data Science blog the most useful in making sense of the field and find "free" resources to building your skills.
Course: Introduction to Machine Learning and Pattern Recognition (EECE 5644) from the Electrical and Computer Engineering Department
Student: Yunus Cem Yılmaz
Comments: I took this course on Machine Learning in Fall 2019. The class is heavily based on probability and is quite math intensive. The main problem that is tackled in it is the classification of data into certain groups with minimum error of classification (which is somewhat different from our purpose in using econometrics as economists). Though a lot of it overlaps with the math in econometrics (both the discussions on probability and matrix algebra are similar, even though this course focuses more on probability and less on matrix algebra), due to the different aims of the two fields, I believe it helps form some perspective on our work and assumptions. I have also attached a link to the syllabus above.
The class itself is somewhat challenging conceptually and all the engineering students take two courses a semester, so the homework and take home exams take a lot longer than most economics courses. I would highly suggest not taking three (or four) courses in a semester while taking this course. It is also important to note that machine learning people refer to everything with a different name compared to economists, which gets frustrating at times.
Google Sites
Report abuse