liveBook · Manning

Target analysis

As explained in Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI

Target analysis is the examination of a prediction target's values and distribution to assess its suitability for modeling and evaluation.

Target analysis examines a prediction target’s values and distribution before modeling. It matters because targets with many zeros, fat tails, or multiple modes can cause some algorithms to underfit. section 4.2.1

A practical target-analysis workflow includes:

  • Plot the target with a histogram to reveal concentration, peaks, skew, and long tails. section 4.2.1
  • Use a boxplot to locate the core distribution and identify extreme values. section 4.2.1
  • Compare transformations or restricted ranges when extreme values obscure the main pattern; a log transformation can make price more symmetrical but may leave tail extremes. section 4.2.1
  • Choose a target formulation deliberately: continuous regression, binary classification using a mean or median threshold, or multiclass bins such as price quintiles. section 4.2.1
data[["price"]].hist(bins=10)

A pandas histogram provides the first visual check of target concentration and skew. section 4.2.1

How Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI covers it

How deep it goes
Explains histograms, boxplots, transformations, range filtering, and three target formulations, but stops short of algorithm-specific treatment.
Examples
Uses Airbnb price histograms and boxplots, log-transformed prices, capped price ranges, thresholds, and price quintiles.
What you can do after
Evaluate target suitability and formulate it as regression, binary classification, or multiclass prediction.
How it connects
Connects exploratory data analysis with histograms, boxplots, log transformation, regression, and classification.
Cover of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
liveBookmanning.com
Read Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI on liveBook Get the book at manning.com

This explainer was generated by Manning's knowledge graph from the text of Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI. The section links point to the parts of the book it draws on.