Reasonability
The degree to which a data pattern meets expectations.
- •Data patterns and trends align with business expectations and known behaviors.
- •Early identification of unexpected or anomalous data that may indicate underlying issues.
- •Increased confidence in data that follows logical and predictable patterns.
- •Better basis for forecasting and planning if historical patterns are reasonable.
- •Data exhibits erratic, unexplainable, or counter-intuitive patterns, raising suspicion.
- •Difficulty in distinguishing genuine anomalies from systemic data quality problems.
- •Reduced trust in data if it frequently deviates from expected behaviors without clear cause.
- •Flawed forecasts if based on unreasonable historical data patterns.
Grade
Logistics: Monthly maintenance costs for port equipment show expected seasonal variations (e.g., higher in off-peak seasons when more maintenance can be scheduled).
Retail: Sales of winter clothing show an expected increase during colder months and a decrease during summer.
Utility: Electricity usage patterns for a commercial building align with its known business hours and operational load.
Logistics: Reported daily container throughput for the terminal suddenly drops to zero for a full day without any explanation (e.g., not a public holiday, no known strike or system outage).
Retail: Online sales figures show a 1000% increase overnight for a specific product without any corresponding marketing campaign or external event.
Utility: Water consumption for a household shows a sustained tenfold increase compared to its historical average, suggesting a possible leak or meter malfunction.