Fairness metrics in ML Python - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Equal Opportunity in Fairness Metrics

Which statement best describes the Equal Opportunity fairness metric in machine learning?

A It requires that the overall accuracy is equal across different groups.

B It requires that the false positive rates are equal across different groups.

C It requires that the true positive rates are equal across different groups.

D It requires that the predicted positive rates are equal across different groups.

💡 Hint

Think about which error type Equal Opportunity focuses on balancing.

Equal Opportunity demands that the model correctly identifies positive cases equally well across groups, meaning the true positive rates should be the same.

❓ Predict Output

intermediate

Output of Fairness Metric Calculation

Given the following confusion matrices for two groups, what is the difference in false positive rates (FPR) between Group A and Group B?

Group A: TP=40, FP=10, TN=50, FN=5
Group B: TP=30, FP=20, TN=40, FN=10

A 0.17

B 0.20

C 0.10

D 0.25

💡 Hint

FPR = FP / (FP + TN). Calculate for each group and subtract.

Group A FPR = 10 / (10 + 50) = 0.1667; Group B FPR = 20 / (20 + 40) = 0.3333; Difference = 0.3333 - 0.1667 = 0.1666 ≈ 0.17.

❓ Model Choice

advanced

Choosing a Model to Optimize Demographic Parity

You want to build a classifier that satisfies Demographic Parity. Which model choice below is most likely to help achieve this?

A A model trained with a fairness constraint that equalizes predicted positive rates across groups.

B A model trained to minimize false negative rates only.

C A model trained to maximize overall accuracy without constraints.

D A model trained with a loss function ignoring group membership.

💡 Hint

Demographic Parity focuses on equalizing positive predictions, not just accuracy.

Demographic Parity requires the predicted positive rates to be equal across groups, so training with a constraint targeting this is best.

❓ Metrics

advanced

Interpreting Disparate Impact Metric

What does a Disparate Impact value of 0.6 indicate about a model's fairness?

A The model's false positive rate is 60% higher for the privileged group.

B The model favors the unprivileged group by predicting positives more often.

C The model has 60% accuracy on the unprivileged group.

D The model predicts positive outcomes for the unprivileged group at 60% the rate of the privileged group.

💡 Hint

Disparate Impact compares positive prediction rates between groups.

A Disparate Impact of 0.6 means the unprivileged group receives positive predictions at 60% the rate of the privileged group, indicating potential bias.

🔧 Debug

expert

Debugging Fairness Metric Calculation Code

What error will this Python code raise when calculating the statistical parity difference?

def stat_parity_difference(y_pred, group):
    pos_rate_priv = sum(y_pred[group == 0]) / len(y_pred[group == 0])
    pos_rate_unpriv = sum(y_pred[group == 1]) / len(y_pred[group == 1])
    return pos_rate_unpriv - pos_rate_priv

# y_pred = [1, 0, 1, 1], group = [0, 1, 0]

ML Python

def stat_parity_difference(y_pred, group):
    pos_rate_priv = sum(y_pred[group == 0]) / len(y_pred[group == 0])
    pos_rate_unpriv = sum(y_pred[group == 1]) / len(y_pred[group == 1])
    return pos_rate_unpriv - pos_rate_priv

# y_pred = [1, 0, 1, 1], group = [0, 1, 0]

A No error; the function returns a float value.

B TypeError because boolean indexing is not supported on lists.

C IndexError due to mismatched lengths of y_pred and group arrays.

D ZeroDivisionError because one group has zero members.

💡 Hint

Check the data types and operations used for indexing.

Boolean indexing like y_pred[group == 0] works on numpy arrays, but y_pred and group are lists here, so this raises a TypeError.

Practice

1. What is the main purpose of fairness metrics in machine learning models?

easy

A. To improve the speed of model training

B. To check if the model treats different groups equally

C. To increase the size of the training dataset

D. To reduce the number of model parameters

Solution

1. Step 1: Understand fairness metrics

   Fairness metrics are designed to measure if a model treats different groups fairly and without bias.

2. Step 2: Compare options

   Options B, C, and D relate to performance or data size, not fairness.

3. Final Answer:

   To check if the model treats different groups equally -> Option B

4. Quick Check:

   Fairness metrics = check equal treatment [OK]

Hint: Fairness metrics check equality across groups [OK]

Common Mistakes:

• Confusing fairness with accuracy
• Thinking fairness improves training speed
• Mixing fairness with data size

2. Which of the following is a correct way to calculate demographic parity difference between two groups?

easy

A. Sum of false negatives in both groups

B. Ratio of training samples in each group

C. Difference in positive prediction rates between groups

D. Difference in model training times

Solution

1. Step 1: Recall demographic parity definition

   Demographic parity measures if the positive prediction rates are similar across groups.

2. Step 2: Evaluate options

   Difference in positive prediction rates between groups matches this definition. Options A, C, and D are unrelated to demographic parity.

3. Final Answer:

   Difference in positive prediction rates between groups -> Option C

4. Quick Check:

   Demographic parity = positive rate difference [OK]

Hint: Demographic parity = compare positive rates [OK]

Common Mistakes:

• Using false negatives instead of positive rates
• Confusing sample ratios with fairness metrics
• Mixing training time with fairness

3. Given the following confusion matrices for two groups, what is the equal opportunity difference? Group A: TP=40, FN=10, FP=20, TN=30 Group B: TP=30, FN=20, FP=15, TN=35

medium

A. 0.25

B. 0.10

C. 0.05

D. 0.20

Solution

1. Step 1: Calculate true positive rates (TPR) for both groups

   TPR = TP / (TP + FN). For Group A: 40 / (40 + 10) = 0.8. For Group B: 30 / (30 + 20) = 0.6.

2. Step 2: Find equal opportunity difference

   Equal opportunity difference = |0.8 - 0.6| = 0.20.

3. Final Answer:

   0.20 -> Option D

4. Quick Check:

   Equal opportunity difference = |TPR_A - TPR_B| = 0.20 [OK]

Hint: Equal opportunity = difference in true positive rates [OK]

Common Mistakes:

• Confusing false positive rate with true positive rate
• Not dividing by (TP + FN)
• Ignoring absolute difference

4. You have this Python code to compute statistical parity difference but it gives wrong results:

def stat_parity_diff(y_true, y_pred, group):
    pos_rate_group1 = sum(y_pred[group == 1]) / len(y_pred[group == 1])
    pos_rate_group0 = sum(y_pred[group == 0]) / len(y_pred[group == 0])
    return pos_rate_group0 - pos_rate_group1

What is the main bug?

medium

A. The difference sign is reversed; should be group1 - group0

B. Using y_true instead of y_pred for positive rates

C. Not handling division by zero if group has no samples

D. Using sum instead of mean for positive rate

Solution

1. Step 1: Understand statistical parity difference

   It is usually calculated as positive rate of group 1 minus positive rate of group 0.

2. Step 2: Check code difference calculation

   The code returns pos_rate_group0 - pos_rate_group1, which reverses the sign.

3. Final Answer:

   The difference sign is reversed; should be group1 - group0 -> Option A

4. Quick Check:

   Sign order matters in parity difference [OK]

Hint: Stat parity = group1 rate minus group0 rate [OK]

Common Mistakes:

• Mixing up group order in subtraction
• Ignoring zero division errors
• Confusing y_true and y_pred

5. You want to ensure your loan approval model is fair by equalizing false positive rates (FPR) across two groups. Given these FPRs: Group X: 0.10 Group Y: 0.25 Which action best reduces this fairness gap?

hard

A. Adjust the model threshold for Group Y to be more strict

B. Increase training data size for Group X

C. Remove Group Y samples from training

D. Use accuracy as the only metric to evaluate fairness

Solution

1. Step 1: Understand false positive rate difference

   Group Y has a higher FPR (0.25) than Group X (0.10), meaning more false alarms for Group Y.

2. Step 2: Choose action to reduce FPR gap

   Adjusting the decision threshold for Group Y to be more strict reduces false positives, lowering FPR closer to Group X.

3. Final Answer:

   Adjust the model threshold for Group Y to be more strict -> Option A

4. Quick Check:

   Threshold tuning reduces FPR gap [OK]

Hint: Higher threshold for high FPR group to reduce false positives [OK]

Common Mistakes:

• Ignoring threshold adjustment
• Removing data harms fairness
• Using accuracy alone misses fairness issues