Overview

This course benefits from having its entire syllabus available online.

The class is notably very easy. It is a good choice for those new to OMSCS, python, numpy, pandas, or machine learning. Ironically, it’s also in very high demand among students, so it is unlikely you get to take it as your first class (though I was able to take it as my second). It has considerably less educational value after you have taken any other machine learning or python-intensive course. But it’s a great course to pair with a harder class if you are looking to work ahead or put in a couple hours a week (or honestly less).

Practical Tips

• Every project has a rubric. Check, double check, and then sleep on it for a night and then triple check that your project addresses every bullet and question from the rubric. Overlooking a rubric detail is easily the number one source of lost points.

• There are several videos listed under the ‘online readings/videos’ that are directly related to the projects. The professor walks you through how to do the project step-by-step. I literally had my IDE open, paused the video, and coded along side him. I highly recommend this; I also think he was entirely too hand-holdy for a graduate course.

• Each project is weighted differently. They are roughly proportional to how long it will take to complete the project. Plan accordingly.

• The requirements for all the projects are extremely cut-and-dry. The one exception that throws people off is that the technical indicators you use in Project 6 must also be the ones you use in Project 8. That probably won’t mean much to you while you are doing Project 6, but it can actually lead to a frustrating time implementing Project 8. It may be worth at least reading and understanding the specs for Project 8 before submitting Project 6.

• The exam had a couple questions related to The Big Short and What Hedge Funds Really Do. Neither are necessary for the projects, so I would recommend watching/reading those right before the exam.