Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureMedium
A data scientist is preparing a dataset for a regression model that predicts house prices. The dataset includes features such as 'Area_sqft' (ranging from 500 to 5000), 'Number_of_Bedrooms' (1 to 5), and 'Year_Built' (1900 to 2023). Some machine learning algorithms are sensitive to the scale of input features, where features with larger numerical ranges might disproportionately influence the model. Which data preprocessing technique should be applied to ensure all numerical features contribute equally to the model?
- AFeature Scaling
- BOne-Hot Encoding
- CImputation
- DDimensionality Reduction
Show answer & explanationAnswer & explanation
Correct answer: A. Feature Scaling
Feature scaling is a preprocessing technique used to standardize or normalize the range of independent variables or features of data. It ensures that features with larger numerical ranges do not dominate the learning process, allowing all features to contribute equally.
Why the other options are wrong
- B. One-Hot Encoding converts categorical data into a numerical format, which is not applicable to numerical features like 'Area_sqft' or 'Year_Built'.
- C. Imputation deals with missing values in a dataset, not the scale of existing numerical features.
- D. Dimensionality Reduction reduces the number of features in a dataset, which is different from adjusting the scale of existing features.
Feature Scaling
A data preprocessing technique used to standardize or normalize the range of independent variables or features of data. It helps in preventing features with larger values from dominating the learning process.
- Ensures all features contribute equally to the model.
- Common methods include Normalization (Min-Max Scaling) and Standardization (Z-score scaling).
- Important for algorithms sensitive to feature magnitudes, like SVMs, K-Nearest Neighbors, and neural networks.
Memory trick: Cleaning and shaping data for the AI's dinner.