Homework 1: Introduction to Machine Learning
- Submissions
- 659
- Completion
- 54.5%
- Median score
- 7
- Lecture time
- 4h
- Homework time
- 1h
- Total time
- 5h
Machine Learning Zoomcamp 2024
Course-level participation, homework, and project statistics.
Median time and score by homework. Hover values on desktop for interquartile ranges.
| Homework | Submissions | Completion | Lecture time | Homework time | Total time | Median score |
|---|---|---|---|---|---|---|
| Homework 1: Introduction to Machine Learning | 659 | 54.5% | 4h | 1h | 5h | 7 |
| Homework 2: Machine Learning for Regression | 468 | 38.7% | 5h | 3h | 8h | 5 |
| Homework 3: Machine Learning for Classification | 385 | 31.8% | 5h | 3h | 8h | 6 |
| Homework 4: Evaluation Metrics for Classification | 324 | 26.8% | 4h | 3h | 7h | 6 |
| Homework 5: Deploying Machine Learning Models | 275 | 22.7% | 4h | 3h | 8h | 6 |
| Homework 6: Decision Trees and Ensemble Learning | 234 | 19.3% | 4h | 3h | 7h | 6 |
| Homework 8: Neural Networks and Deep Learning | 162 | 13.4% | 6h | 3h | 10h | 6 |
| Homework 9: Serverless Deep Learning | 139 | 11.5% | 4h | 4h | 8h | 6 |
| Homework 10: Kubernetes and TensorFlow Serving | 99 | 8.2% | 5.5h | 2h | 9.5h | 7 |
| ML Zoomcamp 2024 Competition | 24 | 2.0% | - | - | - | 9 |
| Article | 17 | 1.4% | - | - | - | 23 |
Ranked by lowest median question score relative to the maximum achievable. Normalizing by question count makes homeworks of different lengths comparable; a lower percentage indicates a harder assignment.
| Rank | Homework | Median score | Score % | Completion |
|---|---|---|---|---|
| 1 | Homework 2: Machine Learning for Regression | 4 / 6 | 66.7% | 38.7% |
| 2 | Homework 3: Machine Learning for Classification | 5 / 6 | 83.3% | 31.8% |
| 3 | Homework 9: Serverless Deep Learning | 5 / 6 | 83.3% | 11.5% |
| 4 | Homework 1: Introduction to Machine Learning | 7 / 7 | 100.0% | 54.5% |
| 5 | Homework 4: Evaluation Metrics for Classification | 6 / 6 | 100.0% | 26.8% |
| 6 | Homework 5: Deploying Machine Learning Models | 6 / 6 | 100.0% | 22.7% |
| 7 | Homework 6: Decision Trees and Ensemble Learning | 6 / 6 | 100.0% | 19.3% |
| 8 | Homework 8: Neural Networks and Deep Learning | 6 / 6 | 100.0% | 13.4% |
| 9 | Homework 10: Kubernetes and TensorFlow Serving | 7 / 7 | 100.0% | 8.2% |
Share of submitted answers that were correct, per question. A lower percentage points to a harder or more confusing question. Participation-only questions are excluded.
| Homework | Question | Correct | Answers | % correct |
|---|---|---|---|---|
| Homework 1: Introduction to Machine Learning | Records count | 646 | 659 | 98.0% |
| Laptop brands | 612 | 659 | 92.9% | |
| Missing values | 571 | 659 | 86.6% | |
| Maximum final price | 651 | 659 | 98.8% | |
| Median value of Screen | 579 | 659 | 87.9% | |
| Sum of weights | 597 | 659 | 90.6% | |
| Homework 2: Machine Learning for Regression | Missing values | 448 | 468 | 95.7% |
| Median for RAM | 463 | 468 | 98.9% | |
| Filling NAs | 237 | 468 | 50.6% | |
| Regularization | 169 | 468 | 36.1% | |
| RMSE spread | 345 | 468 | 73.7% | |
| RMSE on Test | 318 | 468 | 67.9% | |
| Homework 3: Machine Learning for Classification | Mode for the column `education` | 373 | 385 | 96.9% |
| Two features with the biggest correlation | 354 | 385 | 91.9% | |
| Variable with the biggest mutual information score | 363 | 385 | 94.3% | |
| Accuracy on the validation dataset | 364 | 385 | 94.5% | |
| Smallest `C` that leads to the best accuracy on the validation set | 196 | 385 | 50.9% | |
| Homework 4: Evaluation Metrics for Classification | Highest feature AUC | 304 | 324 | 93.8% |
| Validation AUC | 269 | 324 | 83.0% | |
| Precision and recall | 275 | 324 | 84.9% | |
| F1 score threshold | 269 | 324 | 83.0% | |
| STD for 5-Fold CV | 269 | 324 | 83.0% | |
| Best C | 285 | 324 | 88.0% | |
| Homework 5: Deploying Machine Learning Models | Probability of subscription | 237 | 275 | 86.2% |
| Probability of subscription (Flask) | 239 | 275 | 86.9% | |
| Size of base image | 225 | 275 | 81.8% | |
| Probability of subscription (Docker) | 218 | 275 | 79.3% | |
| Homework 6: Decision Trees and Ensemble Learning | Most important featute | 228 | 234 | 97.4% |
| Random forest RMSE | 214 | 234 | 91.5% | |
| Number of estimators | 177 | 234 | 75.6% | |
| Best max_depth | 203 | 234 | 86.8% | |
| Most important feature | 205 | 234 | 87.6% | |
| Eta for XGBoost | 198 | 234 | 84.6% | |
| Homework 8: Neural Networks and Deep Learning | Best loss function | 151 | 162 | 93.2% |
| Total number of parameters | 134 | 162 | 82.7% | |
| Median of training accuracy for all the epochs | 144 | 162 | 88.9% | |
| Standard deviation of training loss for all the epochs | 131 | 162 | 80.9% | |
| Mean of test loss for all the epochs | 144 | 162 | 88.9% | |
| Average of test accuracy for the last 5 epochs | 133 | 162 | 82.1% | |
| Homework 9: Serverless Deep Learning | Size of converted model | 125 | 139 | 89.9% |
| Output index | 132 | 139 | 95.0% | |
| Model output | 117 | 139 | 84.2% | |
| Image size | 112 | 139 | 80.6% | |
| Model output (docker) | 81 | 139 | 58.3% | |
| Homework 10: Kubernetes and TensorFlow Serving | <value> of the probability of getting a subscription | 92 | 99 | 92.9% |
| The smallest deployable computing unit | 96 | 99 | 97.0% | |
| `Type` of the running service | 97 | 99 | 98.0% | |
| Command to upload docker image | 99 | 99 | 100.0% | |
| Create deployment (<Port>) | 99 | 99 | 100.0% | |
| ML Zoomcamp 2024 Competition | Your score (public) | 0 | 24 | 0.0% |
| Your score (private - after the competition finishes) | 0 | 24 | 0.0% | |
| Article | PR URL | 0 | 17 | 0.0% |
When homework submissions arrive relative to the deadline, across all assignments.
Homework submissions per week, across all assignments. Bars are scaled to the busiest week.
169 students completed the course and received certificates.