The goal of the final project is to show me (and everyone else) that you have learned something in the class. It is an opportunity for you to explore ideas that you see in the lectures and homeworks and extend them. You can even think of your project as first steps towards research in machine learning or its applications.
For this semester’s project, you will work individually on a dataset that we will provide. Participants will be placed on a common leaderboard on Kaggle.
Milestones and Grading
Your project is worth 25% of the class grade. This is broken down across the following milestones:
Project information (10 points): You will need to have registered for the Kaggle competition and made a dummy submission. You should also submit your kaggle user details on Canvas.
Project checkpoint 1 (15 points): For this milestone, you will need to have downloaded the data, and also perhaps run some initial pre-processing on it. You should also have made at least one non-dummy submission on Kaggle. You should submit a one page report on Canvas that describes what you did so far, descriptive statistics about the dataset, and your plan till the next milestone.
Project checkpoint 2 (30 points): This milestone is similar to the previous one. You will need to have made at least two additional submissions to Kaggle. You should submit a one-page report detailing updates after the first milestone, any challenges you have faced, and your plan for the rest of the semester.
Final report (45 points): By this time, you should have made at least six non-dummy submissions on Kaggle totally. You should submit a final report of at most six pages that is structured like a small research paper. Broadly speaking it should describe:
- An overview of the project
- What are the important ideas you explored?
- What ideas from the class did you use?
- What did you learn?
- A summary and discussion of results
- If you had much more time, how would you continue the project?
Each of these components will be equally weighted in the report grade.