Grading Principles and Guidelines
👨💻 Coursework:
-
Homework Assignments (15%): Three homework assignments will be given, each requiring submission of a well-documented Jupyter Notebook.
- Homework 1 (5%): Implementing k-fold cross-validation
- Homework 2 (5%): Practicing ALS-related algorithms
- Homework 3 (5%): Prototyping neural networks in recommender systems using TensorFlow
- InClass Kaggle Competition (50%): Open-book InClass Kaggle Competition.
- Round 1 (5%): Implement baseline recommender system methods and get familiar with the Kaggle competition platform.
- Round 2 (45%): Implement SVD recommender system methods.
- Final InClass Quiz (coding and exercise) (35%): Basic Python programming and implementation of recommender systems models (during the final lecture of the semester)
📝 Honesty: Our course places very high importance on honesty in coursework submitted by students, and adopts a policy of zero tolerance on academic dishonesty.
📢 (Late) submission: Homework and submissions are submitted via BlackBoard. We will penalize 10% credits per 12 hours for the late submission (up to a maximum of 50% penalization.).