BenchMark Quizzes by MDFT Pro

Identify Process For Creating Additional Model Features

Claire, the Data Preparation Specialist at MDFT Pro, is working with a dataset of student performance metrics to build a predictive model for course completion rates. MDFT Pro, a well-known training agency, has basic data about students including enrollment dates, course difficulty levels, and assessment scores, but Claire believes the model could be more accurate with additional derived information. She wants to create new data points such as “days since enrollment,” “average score improvement rate,” and “course difficulty relative to student experience level” by combining and transforming the existing data fields to provide richer input for the machine learning algorithm.

What process is Claire using to create these additional data points from existing information to improve model performance?

Choose the correct answer from the options below.

Explanations for each answer:

Feature engineering is correct. Feature engineering involves creating new features from existing data through transformations, combinations, and calculations to improve model performance and capture important patterns.
Feature selection is incorrect. Feature selection chooses the most relevant existing features and removes less important ones, rather than creating new additional features.
Model evaluation is incorrect. Model evaluation assesses model performance using metrics and validation techniques, not the creation of new features from data.
Model training is incorrect. Model training teaches algorithms to learn patterns from data, but doesn't involve creating additional features from the existing dataset.

Learn more about feature engineering:

Feature Engineering

Exam Preparation Quiz

Identify Process For Creating Additional Model Features