How to prevent unfair bias in ML datasets?
You are developing a model to help your company create more targeted online advertising campaigns. You need to create a dataset that you will use to train the model. You want to avoid creating or reinforcing unfair bias in the model. What should you do? (Choose two.)
Community Votes
84% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.
Community Insight
Stratified sampling ensures minority representation in data, while fairness tests validate model equity; the trap is choosing random sampling, which fails to fix skewed distributions.
To prevent unfair bias in advertising models, use a stratified sample for training data to ensure all groups are represented and conduct fairness tests on the model. Community consensus confirms options D and E are correct.
Choosing Option C (random sample) is incorrect because it does not guarantee the representation of minority groups in skewed production traffic, leading to potential model bias.
Community Discussion (13 comments)
AB_C
👍 3
Selected: E
D&E - right
wences
👍 2
Selected: D
From my statistical point of view, D and E will mitigate the effect of bias.
AzureDP900
👍 1
D and E is right answer, question asks us to select 2 right answers • To avoid creating or reinforcing unfair bias in the model, you should collect a representative and diverse dataset (option D) that includes a stratified sample of production traffic. This ensures that your training data is inclusive and accurately represents the diversity of your target audience. • Once you have collected your training dataset, you should conduct fairness tests across sensitive categories and demographics on the trained model (option E). This involves evaluating whether the model treats different demographic groups fairly and without bias. If biases are detected, you can take steps to mitigate them and ensure that your model is fair and accurate.
AzureDP900
👍 3
D and E is right answer, question asks us to select 2 right answers • To avoid creating or reinforcing unfair bias in the model, you should collect a representative and diverse dataset (option D) that includes a stratified sample of production traffic. This ensures that your training data is inclusive and accurately represents the diversity of your target audience. • Once you have collected your training dataset, you should conduct fairness tests across sensitive categories and demographics on the trained model (option E). This involves evaluating whether the model treats different demographic groups fairly and without bias. If biases are detected, you can take steps to mitigate them and ensure that your model is fair and accurate.
dija123
👍 1
Selected: D
Agree with D and E
omermahgoub
👍 3
Selected: D
D. Stratified sampling to ensure the different demographic groups or categories are proportionally represented in the training data. This helps mitigate bias that might arise if certain groups are under-represented. E. Fairness tests can reveal disparities in how the model treats different populations, allowing you to identify and address potential biases.
MultiCloudIronMan
👍 2
Selected: D
D and E is the two answers. Two selections are required
CHARLIE2108
👍 2
Selected: D
I went D, E
guilhermebutzke
👍 1
Selected: D
DE D. Collect a stratified sample of production traffic to build the training dataset: This ensures that the training data represents the diverse demographics that will be targeted by the advertising campaigns. Random sampling might unintentionally underrepresent certain groups, leading to biased model outputs. E. Conduct fairness tests across sensitive categories and demographics on the trained model: This allows you to identify and address any potential biases that may have emerged during the training process. Evaluating the model's performance on different groups helps ensure fair and responsible deployment.
daidai75
👍 1
Selected: D
I go for D & E: A stratified sample ensures that the training data represents the distribution of the target population across relevant demographics or other sensitive categories. This helps mitigate bias arising from underrepresented groups in the data. Regularly testing the model for fairness across sensitive categories helps identify and address potential bias issues before deploying the model in production. This can involve metrics like precision, recall, and F1 score for different demographic groups.
b1a8fae
👍 3
Selected: D
D E. ChatGPT explanation below (but I think makes quite a lot of sense) Collect a Stratified Sample (Option D): Stratified sampling involves dividing the population into subgroups (strata) and then randomly sampling from each subgroup. This ensures that the training dataset represents the diversity of the population, helping to avoid biases. By collecting a stratified sample of production traffic, you are more likely to have a balanced representation of different demographic groups, reducing the risk of biased model outcomes. Conduct Fairness Tests (Option E): After training the model, it's crucial to conduct fairness tests to evaluate its performance across different sensitive categories and demographics. This involves measuring the model's predictions and outcomes for various groups to identify any disparities. Fairness tests help you assess and address biases that may have been inadvertently introduced during the training process.
shadz10
👍 1
Selected: C
C, D - Conducting fairness tests across sensitive categories and demographics on the trained model is indeed important. However, this option focuses on post-training analysis rather than dataset creation. While it's a crucial step for ensuring fairness, it doesn't directly address how to create a training dataset to avoid bias. Hence C,D
pikachu007
👍 1
Selected: D
D. Stratified Sampling: Randomly sampling your data might not accurately represent the diversity of your target audience, potentially introducing bias by over- or under-representing certain demographics. Stratified sampling ensures your training dataset reflects the distribution of sensitive features (e.g., age, gender, income) observed in your production traffic, helping mitigate bias during model training. E. Fairness Testing: Simply collecting unbiased data isn't enough. Regularly testing your trained model for fairness across sensitive categories is crucial. This involves measuring and analyzing metrics like accuracy, precision, recall, and F1 score for different demographic groups. Identifying disparities in performance can trigger further investigation and potential re-training to address bias.
Comments & Corrections
No comments yet — spotted an error or have a note? Share it below.
Expert Analysis
Why the Answer Is Correct
Option D ensures that the training dataset reflects the actual diversity of the population, particularly minority groups that might be lost in a random sample. Option E is necessary to audit the model's performance across different demographics to detect and mitigate disparate impact. These two steps cover data preparation and model validation, which are critical for Responsible AI.Why the Other Options Are Wrong
Option A is incorrect because simply adding demographic features does not prevent bias; the data distribution matters more. Option B introduces selection bias by excluding less frequent groups. Option C is a common trap; while random sampling is a standard practice, it is insufficient for fairness goals because it often underrepresents minority classes in imbalanced real-world data.Community Comment Notes
The community strongly supports D and E, with multiple comments explaining that stratified sampling is statistically required for representation. One dissenting comment (Comment 9) suggested C and D, arguing E is post-training, but the majority and exam guidelines emphasize that fairness testing is a mandatory step in the bias mitigation workflow.Official Reference
Exam Strategy
Always pair 'stratified sampling' with 'fairness testing' in Responsible AI questions to cover both the data input and model output phases of the ML lifecycle.
Related Analysis
Practice All PMLE Questions
Access 65 questions with complete answers and detailed explanations.
View Full PMLE Practice Test →