liveBook · Manning

Customer satisfaction

As explained in Starting Data Analytics with Generative AI and Python

Customer satisfaction is the degree to which customers view a product or service favorably in relation to their expectations.

Customer satisfaction measures how favorably customers view a product or service against their expectations. A star rating gives a quick signal; review analysis explains what drives it. section 5.3.1

Use customer satisfaction analysis to:

  • Identify recurring strengths, such as praise for battery life, durability, or customer service. section 5.3.1
  • Locate problems by comparing positive and negative review terms or separating review scores into positive and negative groups. section 5.3.1 section 3.3.3
  • Track changing preferences, such as increasing mentions of eco-friendly features or sustainable packaging. section 5.3.1 section 5.5.1
  • Compare satisfaction across product categories, sellers, cities, or states while checking whether the comparison supports a useful business decision. section 3.1 section 3.4.4

From an oversized chart to a useful comparison

A grouped chart of every review score by product category can become unreadable. First combine scores into positive ratings of 4–5 and negative ratings of 1–3; then aggregate product categories into broader groups. Inspect the result rather than accepting the generated visualization automatically. section 3.3.3

Treat satisfaction as evidence rather than a verdict. Validate charts against raw reviews, question arbitrary score cutoffs, and discuss useful aggregations with stakeholders before acting. section 3.3.3 section 3.1

How Starting Data Analytics with Generative AI and Python covers it

How deep it goes
Explains ratings, review terms, aggregation, visualization, and group comparisons, but stops short of causal claims about satisfaction.
Examples
Uses star ratings, review terms, product categories, sustainable packaging, seller locations, and state-level review scores.
What it assumes
Assumes customer orders, reviews, ratings, products, sellers, and locations; introduces practical questions for analyzing those records.
What you can do after
Evaluate satisfaction by building review distributions, filtering keywords, aggregating categories, and comparing sellers or regions.
How it connects
Connects customer reviews, sentiment analysis, keyword search, descriptive analytics, review scores, and confidence intervals.

Also explained in

Compare how 4 books explain customer satisfaction →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Starting Data Analytics with Generative AI and Python. The section links point to the parts of the book it draws on.