An aggressive discount can increase orders without improving shopper value or profitability.
CRO guardrails: margin, returns and errors
Measure more than completed purchases. A change increasing errors, returns or discount cost can harm the business.
Research context: Microsoft Research · Reliable online experiments ↗
Choose a few justified guardrails and adequate follow-up. Never promise quick conclusions with low traffic.
Try the pattern
Task and expected result
- 01
Describe the desired outcome and one possible harm from the change.
- 02
Define how refunds link to the original order.
- 03
Write the decision rule before results or temporary spikes appear.
How to investigate value
Define audience, exposure, denominator and primary outcome before starting. Record what could invalidate the data.
Watch for side effects
Data loss, incorrect variant allocation, returns/refunds, margin, accessibility and mobile performance.
This is a proposed investigation, not a measured result. Choose one hypothesis and define the audience before testing.
Build a measurement plan for this concept ↗