How to ensure ML model transparency and explainability for stakeholders?

AIF-C01 By islever Editorial Last updated Aug 3, 2026

Short answer

B Partial dependence plots (PDPs)

Question

A company makes forecasts each quarter to decide how to optimize operations to meet expected demand. The company uses ML models to make these forecasts. An AI practitioner is writing a report about the trained ML models to provide transparency and explainability to company stakeholders. What should the AI practitioner include in the report to meet the transparency and explainability requirements?

Code for model training
Partial dependence plots (PDPs) Correct Answer
Sample data for training
Model convergence tables

Key Takeaways

This question tests the ability to distinguish between raw technical artifacts (code, data, convergence tables) and stakeholder-friendly explainability visualizations, with PDPs being the industry-standard tool for feature impact analysis.

Partial Dependence Plots (PDPs) are the primary tool for communicating ML model transparency and explainability to non-technical stakeholders. They visually illustrate how individual features impact model predictions, making them the correct choice for reporting on trained models.

Common mistake: Candidates often choose 'Code for model training' (Option A) because they associate transparency with full access to the underlying implementation, failing to recognize that stakeholders need interpretable insights, not raw code.

Expert Analysis

Understanding Model Transparency and Explainability

In the context of machine learning operations, transparency and explainability are critical for building trust with business stakeholders. When an AI practitioner is tasked with writing a report for non-technical audiences, the goal is to provide clear, interpretable insights into how the model makes decisions.

Why Partial Dependence Plots (PDPs) Are Correct

Partial Dependence Plots (PDPs) are visualization tools that show the marginal effect of one or more input features on the predicted outcome of a machine learning model. They hold all other features constant and plot the average prediction as the feature of interest varies. This allows stakeholders to:

Visually understand how changes in specific input variables (e.g., seasonality, pricing, inventory levels) affect demand forecasts.
Identify non-linear relationships and interaction effects between features.
Validate model behavior against domain knowledge without needing to read code or inspect raw data.

Community consensus is unanimous (100% vote for B), with multiple users confirming that PDPs are specifically designed for stakeholder-facing explainability.

Why Other Options Are Incorrect

Option A (Code for model training): While sharing code provides technical transparency, it is not useful for business stakeholders who need to understand what the model does, not how it is implemented. Code is not an explainability tool.
Option C (Sample data for training): Providing sample data does not explain model behavior or decision-making logic. It may raise privacy and data governance concerns and does not contribute to model interpretability.
Option D (Model convergence tables): Convergence tables are technical diagnostics used during model training to monitor optimization progress (e.g., loss over epochs). They are meaningful only to ML engineers and provide no insight into how the model makes predictions for stakeholders.

Key Takeaway

When the question emphasizes transparency and explainability for stakeholders, always look for interpretability tools like PDPs, SHAP values, or LIME explanations rather than raw technical artifacts.

Official Reference

These links open the official vendor documentation in a new tab.

Exam Strategy

When a question mentions 'stakeholders,' 'transparency,' or 'explainability,' eliminate options that are purely technical artifacts (code, raw data, training logs). Always choose the option that provides visual or intuitive interpretation of model behavior.

Community Votes

100%

100% of anonymous learners picked answer B. Votes are pick records left by other test-takers — they are not the verified answer.

Discussion 9 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 9

jove 👍 9 Answered B

B. Partial Dependence Plots (PDPs) Explanation: Partial Dependence Plots (PDPs) are useful tools for understanding the relationship between specific features and the model's predictions, making it easier to see how changes in input variables affect the forecast. PDPs are particularly helpful for stakeholders because they visually show the impact of individual features on predictions without requiring a deep understanding of the model's inner workings.
swat2024 👍 4 Answered B

anyone able to provide all questions. i can see only first 32 questions
kopper2019 👍 2 Answered B

AWS certification exams are introducing new question types, including ordering, matching, and case study questions, alongside traditional multiple choice and multiple response formats. The ordering type requires arranging selected responses in the correct sequence, while matching questions involve linking statements to prompts. Case studies recycle a scenario across multiple questions, allowing candidates to save time by understanding the context once. Each question is evaluated independently, meaning it's crucial to answer all parts correctly to receive credit.
Rcosmos 👍 1 Answered B

Explicação:Gráficos de dependência parcial (Partial Dependence Plots - PDPs) são usados para mostrar como uma variável de entrada afeta a previsão do modelo, mantendo as outras variáveis constantes.São ferramentas poderosas de explicabilidade e transparência, especialmente para partes interessadas não técnicas. Eles ajudam a visualizar a relação entre características importantes e as previsões do modelo, respondendo perguntas como: "Se aumentarmos o orçamento em marketing, o que acontece com a demanda prevista?"
Jessiii 👍 1 Answered B

PDPs help in explaining the relationship between the features and the model’s predictions, offering transparency into how the model makes decisions, which is critical for explainability to stakeholders. PDPs show how changes in a feature impact the model's output, thus helping to provide an understanding of the model's behavior.

Show 4 more comments

rason5 👍 1 Answered B

B is the answer Thanks to P A S S 4 S U R E H U B
Owolabi19 👍 1 Answered B

Answer:B. Partial dependence plots (PDPs)
preetgoswami 👍 1 Answered B

B. Partial dependence plots (PDPs)
sacha12 👍 1

I think B is correct

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Practice All AIF-C01 Questions

Access 100 questions with complete answers and detailed explanations.

View Full AIF-C01 Practice Test →

← Back to AIF-C01 Study Guide