Answer-first summary for fast verification
Answer: Build a logistic regression model in scikit-learn, and interpret the model's output coefficients to understand feature impact.
The question emphasizes 'simple interpretability' and understanding 'which features led to the prediction.' Logistic regression (option C) is optimal because its coefficients directly represent the impact of each feature on the log-odds of churn, making them straightforward to interpret for business stakeholders. Linear regression (option D) is less suitable for binary classification problems like churn prediction. Complex models like DNN with SHAP (A) or LSTM with attention (B) offer post-hoc interpretability but are inherently less transparent and harder for non-technical stakeholders to understand directly. The community discussion shows consensus for C, with the commenter explicitly stating 'Definitely C in my opinion' despite the initial answer being A, indicating recognition that simpler, inherently interpretable models are preferred when explainability is the primary requirement.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
Your company's business stakeholders need to understand the key factors driving customer churn to inform their strategy. You must build a customer churn prediction model that prioritizes straightforward interpretability of the results. Which ML framework and modeling technique should you choose to best explain which specific features influenced each prediction?
A
Build a TensorFlow deep neural network (DNN) model, and use SHAP values for feature importance analysis.
B
Build a PyTorch long short-term memory (LSTM) network, and use attention mechanisms for interpretability.
C
Build a logistic regression model in scikit-learn, and interpret the model's output coefficients to understand feature impact.
D
Build a linear regression model in scikit-learn, and interpret the model's standardized coefficients to understand feature impact.