Learn about feature engineering, the process of creating new features from raw data to improve machine learning model performance, in this detailed explanation of an AI-900 certification exam practice question. Discover why feature engineering is key for generating additional features compared to model evaluation, feature selection, and model training.
Table of Contents
Question
Which of these methods is used to generate additional features? Select the correct option.
A. Model evaluation.
B. Feature engineering.
C. Feature selection.
D. Model training.
Answer
B. Feature engineering.
Explanation
Feature engineering is the correct answer because it refers to the process of creating new features (predictor variables) from the existing raw data to help machine learning algorithms achieve better performance.
The goal of feature engineering is to generate additional informative features that weren’t originally present in the dataset. This often involves:
- Transforming and combining existing features in creative ways
- Extracting hidden patterns, trends, and relationships
- Deriving domain-specific features based on knowledge of the problem
For example, if building a house price prediction model, you could engineer new features like “price per square foot” by combining existing features for price and square footage. Or extract the number of bathrooms and bedrooms from a text description field.
In contrast, the other options are separate steps in the machine learning workflow:
- Model evaluation assesses a trained model’s performance on unseen test data
- Feature selection identifies the most relevant features to keep and discards redundant/irrelevant ones
- Model training fits the model to the training data so it can learn patterns
So while feature selection reduces features and model training fits the model to data, only feature engineering focuses on creating additional new features to improve model performance. That’s why feature engineering is the method used to generate additional features.
Feature engineering involves creating new input features from raw data to improve the performance of a machine learning model. This process might include transforming variables, combining features, or extracting useful information from existing data.
Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.