The homeworks will each have two components:

  • A conceptual component in which you will be asked to read a case study, article, or research paper – about how a data science technique works or doesn’t in practice – and then answer several short answer questions. This part may further include a few short, theoretical (mathematical) questions.
  • A programming component (in Python) in which you will be asked to implement some of the solutions taught in class on either synthetic or real-world data. You may be asked to submit predictions on a test set (e.g., recommendations, or prices at which to sell an item) that will then be scored by the teaching staff.

Homework grading: Each question will be given a score from 0 - 3 points.

  • 0 point: The question was not attempted.
  • 1 point: If you attempt it, but there are either substantial methodological errors or major conceptual misunderstandings of the material
  • 2 points: There are no substantial methodological errors or major conceptual misunderstandings of the material, and the conceptual discussion is sufficient.
  • 3 points: Exceptional solution

We expect that most students will receive 2 points on most homework questions. 3 points will be given for going above and beyond the minimum requirements in the programming portion or conceptual discussion.

Dropping grades and late days

  • We will replace your lowest homework grade with your project grade (if it is higher), so that your composite homework grade will be based on your top three homework scores and final project score, evenly weighted.
  • In addition, you will be allowed three total late days during the semester. These late days allow you to turn in homework up to 24 hours late, with no penalty; you may also use all three late days on a single homework assignment (allowing you to turn it in up to 72 hours late), but that will leave you with no late days for other assignments. When submitting an assignment late, please mark at the top how many late days are used for this assignment and how many you have used before, if any.