Follow the transformation
Define the entity and event that counts.
Define the denominator/population at risk.
Choose a time window and cohort boundary.
Business Analysis · Lesson 73
Funnel Analysis
Funnel Analysis is a business-analysis pattern that converts event or transactional data into a decision-focused measure.
What Funnel Analysis actually means
Funnel Analysis is a business-analysis pattern that converts event or transactional data into a decision-focused measure. The numerator, denominator, cohort definition and time window must be explicit for the metric to be comparable.
Funnel Analysis matters because business metrics are often ratios, cohorts or event sequences whose meaning depends on denominator, time window and eligibility rules. Those definitions must stay stable before segments or periods can be compared.
Deeper walkthrough
Read Funnel Analysis as a mechanism, not a recipe
Treat this as a sequence of observable decisions rather than one opaque command. Stage 1: Define the entity and event that counts. Stage 2: Define the denominator/population at risk. Stage 3: Choose a time window and cohort boundary. Final checkpoint: Connect the pattern to a decision rather than reporting a number alone.
Know what would convince you
- Write the decision question, unit of analysis and metric formula in plain language before computing it.
- Reconcile KPI numerators/denominators or grouped totals to source counts for a small slice.
Useful distinctionRate: Events or successes divided by an eligible population.
Click a stage to inspect what happens, what changes, and what should be checked before moving on.
Stage 1
Define the entity and event that…
Define the entity and event that counts. This is an input-preparation stage for Funnel Analysis. Verify the relevant type, shape, units, keys, missingness or assumptions before later steps depend on them.
Input focus: confirm the data/object, units, type, shape and assumptions before the next operation depends on them.
Trace the mechanism step by step
- Define the entity and event that counts.
- Define the denominator/population at risk.
- Choose a time window and cohort boundary.
- Calculate the measure by relevant segment.
- Check denominator size, survivorship and calendar effects.
- Connect the pattern to a decision rather than reporting a number alone.
Make the concept concrete
Demonstration
Python example
# Step 1 — Compute the right-hand expression and store its result in `stages` for the next step.
stages={"visit":1000,"signup":300,"trial":180,"paid":90}
# Step 2 — Compute the right-hand expression and store its result in `prev` for the next step.
prev=None
# Step 3 — Iterate through the collection so the indented block is applied once for each item.
for name,n in stages.items():
# Step 4 — Evaluate this condition and execute the indented branch only when the condition is true.
if prev: print(name, f"step conversion={n/prev:.1%}")
# Step 5 — Compute the right-hand expression and store its result in `prev` for the next step.
prev=nExpected / illustrative result
signup 30.0%; trial 60.0%; paid 50.0%. Step conversion differs from overall visit→paid conversion (9%).
Interpret the result.
For Funnel Analysis, connect the displayed result to the specific input and mechanism above; independently verify one value/state change rather than treating successful execution as proof.
Know what this is — and what it is not
RateEvents or successes divided by an eligible population.GrowthRelative or absolute change between periods.RetentionShare of an initial cohort still active at a later period.Funnel conversionShare progressing from one defined stage to the next.When it is appropriate
Use Funnel Analysis when it connects a clearly framed stakeholder question to measurable evidence and an action or decision.
When to stop or reconsider
Reframe the analysis if the decision, unit of analysis, metric definition, comparison group or time window is still ambiguous; more computation will not repair an undefined question.
Failure modes to recognise
- Starting with a favourite chart/tool before defining the decision and unit of analysis.
- Using an undefined KPI, denominator, cohort or time window and then comparing incomparable numbers.
- Turning association or a descriptive pattern into a causal recommendation without supporting design/evidence.
How to check the result
- Write the decision question, unit of analysis and metric formula in plain language before computing it.
- Reconcile KPI numerators/denominators or grouped totals to source counts for a small slice.
- Test whether the conclusion changes under one reasonable alternative definition or comparison window.
Demonstrate understanding
Try this:
Build a tiny, inspectable example of Funnel Analysis. First define the entity and event that counts. Then define the denominator/population at risk. Write the expected result before running it, and explain one condition that would make the result misleading or invalid.
Write the decision, unit and metric definition first. Use a tiny slice where you can recompute the KPI/table manually and explain what would change the recommendation.
Check reasoning, not memorisation
Before trusting a result from Funnel Analysis, which check provides the strongest evidence that you understand and applied it correctly?
Keep the important distinctions visible
Step 1Define the entity and event that counts.Step 2Define the denominator/population at risk.Step 3Choose a time window and cohort boundary.Step 4Calculate the measure by relevant segment.What to remember
- Funnel Analysis is a business-analysis pattern that converts event or transactional data into a decision-focused measure. The numerator, denominator, cohort definition and time window must be explicit for the metric to be comparable.
- Define the entity and event that counts.
- Starting with a favourite chart/tool before defining the decision and unit of analysis.
- Write the decision question, unit of analysis and metric formula in plain language before computing it.