Your task is to build a regression model for predicting demand for your car rental service for the following quarter.
For scoring your model, you need to define a primary metric which can be used by the Scoring step.
You decide to use the Logistic regression algorithm, and the normalized_mean_absolute_error as primary metric.
Is it an appropriate decision?
Click on the arrows to vote for the correct answer
A. B. C. D.Answer: D.
Option A is incorrect because the selected algorithm is not applicable because Logistic Regression can only be used in classification scenarios.
The selected metric is a valid option for regression tasks.
Option B is incorrect because the selected algorithm is not applicable.
The metric, however, is a valid option for regression tasks.
Option C is incorrect because the selected algorithm is actually not applicable, however selection of normalized_mean_absolute_error as primary metric is a valid option for regression tasks.
Option D is CORRECT because Logistic Regression, despite its name, is an algorithm for classification, not for regression.
Reference:
The decision to use Logistic Regression algorithm for predicting demand for a car rental service may not be appropriate as it is generally used for classification problems, not regression problems. Linear regression or other regression algorithms may be more appropriate.
However, the decision to use normalized_mean_absolute_error as the primary metric for evaluating the model's performance is reasonable. This metric calculates the mean absolute error of the predictions, normalized by the mean absolute error of a baseline model that always predicts the average demand. It is a common metric for regression problems and can provide useful insights into how well the model performs compared to a simple baseline.
In summary, option D is the most appropriate answer. While the selected primary metric is reasonable, the choice of the Logistic Regression algorithm may not be suitable for this specific problem.