liveBook · Manning

Transparency

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

The degree to which a model's operation, predictions, and feature reliance can be understood and assessed by people.

Transparency measures how easily people can understand a model's operation, predictions, and reliance on input features. It matters when selecting models for scientific and business data. section 3.0 section 3.5

Assess transparency through two practical questions:

  • Explainability: can the model's behavior be explained intuitively to business stakeholders, regulators, or other nonspecialists? section 3.2 section 3.2.3
  • Feature importance: can you determine which input features have the greatest effect on the model's behavior? section 3.2 section 3.2.3

House time on the market

A model predicts whether a fresh listing will remain on the market for more or less than a month using city, asking price, transit distance, and historical time on market. This compact dataset makes explanations easier to inspect. section 3.2

Table 3.2 House time on the market dataset (view table figure)

Time on market (weeks)

City

Asking price (thousand $)

Distance to transit station (km)

6

Kitchener

600

10

5

Waterloo

700

5

12

Kitchener

900

20

6

Waterloo

700

15

1

Waterloo

500

5

4

Waterloo

600

5

8

Waterloo

750

5

2

Kitchener

500

5

9

Kitchener

1000

5

4

Waterloo

750

10

Inspect the house listings table used to illustrate how model inputs relate to time on the market. section 3.2

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

How deep it goes
Separates transparency into explainability and feature importance, then compares gradient boosting with deep learning.
Examples
Uses Airbnb price prediction and house time-on-market prediction to compare practical model transparency.
What you can do after
Evaluate model transparency by explaining behavior and identifying influential features for stakeholders or regulators.
How it connects
Links transparency with explainability, feature importance, gradient boosting, deep learning, simplicity, and efficacy.
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

Also explained in

Compare how 19 books explain transparency →

Related concepts

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.