liveBook · Manning

Benchmark

As explained in Effective Data Analysis

A benchmark is a reference value or standard used to evaluate and compare an observed measurement or proportion.

A benchmark is a reference point for comparing a metric’s observed value. Benchmarking is the act of making that comparison. A relevant benchmark puts performance in context and can anchor a goal because it reflects a level of performance already achieved elsewhere. section 7.2.2

Choose a reference that fits the metric and the decision:

  • Compare with organizations similar in industry, size, geography, and type of service when judging a feasible target. section 7.2.1
  • Look for industry averages, peer-reviewed research, or public data from governments and other organizations when those sources measure something relevant. section 7.2.2
  • Examine your own metric’s history alongside the benchmark. Long-term trends—ideally spanning at least two years—help reveal seasonal changes that a single comparison could miss. section 7.2.1

Customer churn

Plotting a company’s customer churn rate against an industry benchmark shows whether its rate tends to be higher. A persistent gap suggests room to improve retention; it does not, by itself, identify which actions will reduce churn. section 7.2.1

Figure 7.8 This chart shows a company’s customer churn rate compared to an industry benchmark. Here, churn tends to be higher than the benchmark, which suggests there may be room for improvement in the customer retention rate.
figure

The chart makes the comparison visible over time: the company’s churn rate tends to exceed the industry benchmark. section 7.2.1

Treat a benchmark as context, not an automatic target. Set an achievable goal using historical patterns, comparable performance, factors that predict the metric, and constraints outside the organization’s control. Then identify actions that could plausibly change the result. section 7.2.1 section 7.2.2

How Effective Data Analysis covers it

How deep it goes
Defines benchmarking, identifies data sources, and gives selection considerations; does not specify a statistical comparison procedure.
Examples
Illustrates comparisons with a customer churn chart and footwear sales measured against public expenditure data.
What it assumes
Assumes a defined metric and calls for historical measurements and comparable reference data before setting targets.
What you can do after
Apply it to compare metric values with relevant references and inform achievable performance targets.
How it connects
Connects benchmarks to metrics, historical trends, seasonality, baselines, and target setting.

Also explained in

Compare how 23 books explain benchmark →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Effective Data Analysis. The section links point to the parts of the book it draws on.