Your company's business stakeholders want to understand the factors driving customer churn to inform their business strategy. You need to build a customer churn prediction model that prioritizes simpl

Question

Options

• ABuild a TensorFlow deep neural network (DNN) model, and use SHAP values for feature
• BBuild a PyTorch long short-term memory (LSTM) network, and use attention mechanisms for
• CBuild a logistic regression model in scikit-learn, and interpret the model's output coefficients to
• DBuild a linear regression model in scikit-learn, and interpret the model's standardized coefficients

• A
  14% (5)
• B
  3% (1)
• C
  75% (27)
• D
  8% (3)

Explanation

The requirement is 'simple interpretability'-business stakeholders need to understand which features drive churn predictions. Logistic regression is inherently interpretable: each coefficient directly quantifies the log-odds contribution of a feature to the predicted probability of churn, making it straightforward to explain to non-technical stakeholders. Option A (TensorFlow DNN with SHAP) uses a complex black-box model; SHAP adds post-hoc interpretability but the model itself is not simply interpretable. Option B (LSTM with attention) is even more complex and suited for sequential data. Option D (linear regression) is for continuous outcomes-churn is a binary classification problem, making linear regression statistically inappropriate. Logistic regression in scikit-learn is the correct, simple, and directly interpretable choice for binary classification.

No community discussion yet for this question.