Machine Learning Zoomcamp 2024

Homework 4: Evaluation Metrics for Classification Statistics

Distribution of scores and reported study time for this homework.

Submissions

325

Median total score

6

Average total score

6

Score distribution

All values are points.

Questions score

Min
-
Median
6.0
Max
6
Q1
5.0
Avg
5.2
Q3
6.0

Learning in public score

Min
-
Median
0.0
Max
7
Q1
0.0
Avg
0.7
Q3
0.0

Total score

Min
-
Median
6.0
Max
14
Q1
5.0
Avg
6.0
Q3
6.0

Time distribution

All values are hours reported by students.

Lectures

Min
0.0
Median
4.0
Max
48.0
Q1
3.0
Avg
5.5
Q3
6.0

Homework

Min
0.0
Median
3.0
Max
20.0
Q1
2.0
Avg
3.7
Q3
4.0

Question breakdown

Correctness and answer distribution per question.

1. Highest feature AUC

304 / 324 correct (93.8%)

1 balance 9 (2.8%)
2 day 4 (1.2%)
3 duration 304 (93.8%)
4 previous 6 (1.9%)

2. Validation AUC

269 / 324 correct (83.0%)

1 0.69 20 (6.2%)
2 0.79 10 (3.1%)
3 0.89 269 (83.0%)
4 0.99 23 (7.1%)

3. Precision and recall

275 / 324 correct (84.9%)

1 0.265 275 (84.9%)
2 0.465 22 (6.8%)
3 0.665 12 (3.7%)
4 0.865 14 (4.3%)

4. F1 score threshold

269 / 324 correct (83.0%)

1 0.02 8 (2.5%)
2 0.22 270 (83.3%)
3 0.42 27 (8.3%)
4 0.62 18 (5.6%)

5. STD for 5-Fold CV

269 / 324 correct (83.0%)

1 0.0001 22 (6.8%)
2 0.006 269 (83.0%)
3 0.06 21 (6.5%)
4 0.26 6 (1.9%)

6. Best C

285 / 324 correct (88.0%)

1 0.000001 18 (5.6%)
2 0.001 14 (4.3%)
3 1 285 (88.0%)

Calculated: 24 October 2024, 14:40