Which ML Model Type Allows Viewing and Adjusting Variable Weights?
A company wants to build a lead prioritization application for its employees to contact potential customers. The application must give employees the ability to view and adjust the weights assigned to different variables in the model based on domain knowledge and expertise. Which ML model type meets these requirements?
Community Votes
100% of anonymous learners picked answer A. Votes are pick records left by other test-takers — they are not the verified answer.
Community Insight
This question tests the concept of model interpretability; logistic regression assigns explicit, human-readable coefficients (weights) to each feature, unlike black-box models such as neural networks or deep learning.
Logistic regression is an interpretable machine learning model that exposes individual feature weights, allowing business users to view and manually adjust them based on domain expertise. This makes it ideal for lead prioritization applications requiring transparent, user-tunable parameters.
Candidates often choose neural networks or deep learning because they are powerful and popular, overlooking that their weights are distributed across many hidden layers and are not meaningfully adjustable by end users.
Community Discussion (5 comments)
Comments & Corrections
No comments yet — spotted an error or have a note? Share it below.
Expert Analysis
Why Logistic Regression is the Correct Answer
The key requirement in this question is the ability for employees to view and adjust the weights assigned to different variables based on domain knowledge. Logistic regression is a linear model that produces a set of explicit, interpretable coefficients—one for each input feature. These coefficients directly represent the weight or importance of each variable in the prediction.
For example, in a lead prioritization model, features like "company size," "industry," or "engagement score" each receive a clear numeric weight. A domain expert can inspect these weights, understand their impact, and manually override them if business logic demands it.
Why the Other Options Are Incorrect
- Deep learning model built on principal components (B): Deep learning models are inherently black-box models. Their weights are distributed across numerous hidden layers and neurons, making individual feature weights impossible to interpret or manually adjust in a meaningful way.
- K-nearest neighbors (k-NN) (C): k-NN is a lazy learner that does not produce explicit feature weights at all. Predictions are based on distance metrics to neighboring data points, so there are no tunable coefficients for employees to adjust.
- Neural network (D): Similar to deep learning, standard neural networks store knowledge in opaque weight matrices across layers. While techniques like SHAP or LIME can approximate feature importance, the weights themselves are not directly adjustable by business users.
Community Consensus
All community voters (100%) selected A, with multiple comments reinforcing that logistic regression's interpretability and transparent coefficients are exactly what the scenario demands. As one user noted, it provides a clear relationship between input features and output predictions, making manual weight adjustment straightforward.
Official Reference
Exam Strategy
When a question emphasizes interpretability, transparency, or the ability for humans to inspect and modify model parameters, always lean toward linear models like logistic regression. Black-box models like neural networks are powerful but fail any requirement involving manual weight adjustment or explainability.
Related Analysis
Practice All AIF-C01 Questions
Access 100 questions with complete answers and detailed explanations.
View Full AIF-C01 Practice Test →