Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureMedium
A data scientist is building a machine learning model to predict the energy consumption of a building. The model uses historical data including temperature, humidity, and occupancy levels. The primary goal is to minimize the average magnitude of errors between the predicted consumption and the actual consumption, regardless of the direction of the error. Which evaluation metric should the data scientist prioritize?
- AAccuracy
- BPrecision
- CMean Absolute Error (MAE)
- DR-squared
Show answer & explanationAnswer & explanation
Correct answer: C. Mean Absolute Error (MAE)
Mean Absolute Error (MAE) measures the average magnitude of the errors in a set of predictions, without considering their direction. It is a suitable metric for regression problems where the goal is to minimize the absolute difference between predicted and actual values.
Why the other options are wrong
- A. Accuracy is typically used for classification problems, measuring the proportion of correct predictions.
- B. Precision is a classification metric that measures the proportion of true positive predictions among all positive predictions.
- D. R-squared (Coefficient of Determination) measures the proportion of variance in the dependent variable that is predictable from the independent variables, not the absolute error magnitude.
Mean Absolute Error (MAE)
A regression metric that measures the average of the absolute differences between predictions and actual observations. It quantifies the average magnitude of errors, without considering their direction.
- Calculated as the average of |actual - predicted|.
- Robust to outliers compared to Mean Squared Error (MSE).
- Units are the same as the target variable, making it easily interpretable.
Memory trick: Measuring how close our predicted line is to the real data points.