Microsoft Azure AI Fundamentals (AI-900)Describe fundamental principles of machine learning on AzureEasy

A data scientist is tasked with preparing a dataset for a machine learning model that will predict whether a customer will purchase a product. The dataset contains a feature called 'Customer_Segment' with nominal categorical values such as 'New Customer', 'Loyal Customer', and 'High-Value Customer'. Which data preprocessing technique should the data scientist use to convert this feature into a suitable format for most machine learning algorithms?

  1. ABinning
  2. BPrincipal Component Analysis (PCA)
  3. CFeature Scaling
  4. DOne-Hot Encoding
Show answer & explanation

Correct answer: D. One-Hot Encoding

One-Hot Encoding is the appropriate technique for converting nominal categorical data into a numerical format that machine learning algorithms can process without implying any ordinal relationship. Each category is transformed into a new binary feature.

Why the other options are wrong

  • A. Binning converts numerical features into categorical bins, which is the opposite of the requirement.
  • B. PCA is a dimensionality reduction technique for numerical data, not for encoding nominal categorical features.
  • C. Feature Scaling adjusts the range of numerical features, not categorical ones.

One-Hot Encoding

A technique used to convert categorical variables into a numerical format that machine learning algorithms can understand. It creates new binary features for each category.

  • Transforms nominal categorical data.
  • Creates a new binary column for each unique category.
  • Avoids implying ordinal relationships between categories.

Memory trick: Categorical data needs a 'hot' new look for the model.

More Describe fundamental principles of machine learning on Azure questions