Find and investigate spreadsheet outliers

Autor: AILesson7 Min. EinrichtungszeitGetestet mit:ChatGPTGeprüft am: 2026-08-28

Schnelle Antwort

Flag unusual values with a method suited to the distribution, then investigate before removal. Angeben: Metric and business meaning, Data profile, Investigation and usage. Erwartetes Ergebnis: Transparent outlier flags, context checks, and keep-correct-remove decisions.

1

Kontext hinzufügen

Dein Text bleibt in diesem Browser. AILesson Prompts sendet ihn nicht an ein Modell oder einen Server.

2

Dein Prompt

Nicht ausgefüllte Felder bleiben als Platzhalter sichtbar, sodass du den Prompt weiterhin kopieren und bearbeiten kannst.

Design a spreadsheet outlier analysis.

Metric, unit, valid range, and groups:
[metric]

Data profile and representative values:
[distribution]

Investigation purpose and policy:
[policy]

Separate impossible values, data-entry errors, rare but valid events, and influential observations. Choose a transparent method appropriate to skew and sample size, such as business-rule limits, IQR, robust z-score, or within-group comparison. Return formulas, thresholds, an OutlierReason field, and a review workflow. Do not delete or winsorize values automatically. Show how conclusions change with and without flagged observations and how each row can be traced to source evidence.
Im Playground ausprobieren
Standardmäßig privatDer Prompt wird lokal in deinem Browser zusammengestellt. Gib keine vertraulichen Informationen in einen KI-Dienst ein, es sei denn, deine Organisation erlaubt dies.

Von der Eingabe zum Ergebnis

Ein ausgearbeitetes Beispiel

Sieh dir an, wie konkreter Kontext dieses Rezept in ein nutzbares Ergebnis verwandelt.

Tatsächliche Eingabe

Metric and business meaning
OrderValue in GBP, nonnegative. Analyze typical order size by CustomerType because Wholesale orders are normally larger than Retail.
Data profile
2,400 orders. Retail n=2,100: Q1 £28, median £46, Q3 £72, max £8,400. Wholesale n=300: Q1 £410, median £690, Q3 £1,100, max £12,500. Three values are negative; one Retail row is £8,400; several Wholesale rows exceed £4,000.
Investigation and usage
Find data errors and understand whether extreme orders distort the average. Every order can be checked against an invoice. Do not remove a valid large order.

Beispielausgabe

Apply the nonnegative business rule first: all three negative values are Invalid and require invoice or source correction. Detect unusual values within CustomerType, not across the mixed population.

For Retail, IQR = 72−28 = 44 and the upper fence is 72+1.5×44 = £138. This intentionally flags many high Retail orders for investigation, not deletion. For Wholesale, IQR = 690 and the upper fence is £2,135. Add group quartiles in a summary table and an OutlierReason column that distinguishes Negative-invalid, Above-group-IQR, and Not-flagged.

The £8,400 Retail order is highly unusual; verify customer type, decimal placement, currency, duplicates, and invoice. If verified, retain it as Rare-valid and explain its influence. Wholesale orders above £4,000 receive the same source check but should not be compared with the Retail threshold.

Report median and IQR as the primary typical-size statistics. Show mean order value with all valid rows and again excluding Rare-valid rows as a sensitivity analysis, while keeping the official total revenue unchanged. Record OrderID, flag, evidence checked, decision, reviewer, and date for every changed classification.

Warum das funktioniert

  1. 1

    Separating invalid from unusual prevents legitimate high-impact events from being erased.

  2. 2

    Sensitivity results reveal whether a small number of observations drives the conclusion.

Ergebnis prüfen

  • Is the detection method appropriate for the metric distribution and groups?

  • Are impossible, erroneous, and rare-valid values labeled separately?

  • Is every correction backed by source evidence?

Sicher nutzen

Häufig gestellte Fragen

Praktische Antworten dazu, wann du dieses Rezept verwenden solltest, was du bereitstellen solltest und wo menschliche Prüfung weiterhin wichtig ist.

What should I prepare before using “Find and investigate spreadsheet outliers”?

For “Find and investigate spreadsheet outliers,” prepare Metric and business meaning, Data profile, and Investigation and usage. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.

When is the “Find and investigate spreadsheet outliers” result not ready to use?

The result is not ready if it does not yet deliver the stated outcome—Transparent outlier flags, context checks, and keep-correct-remove decisions—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.

Which AI tools have recorded tests for “Find and investigate spreadsheet outliers”?

The published test record for “Find and investigate spreadsheet outliers” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.

Weitere Möglichkeiten zum Entdecken

Wo dieses Rezept hineinpasst

Bring die Arbeit voran