Spreadsheet Outlier & Anomaly Finder
Outliers are values that sit far from the rest of your data — often typos, fraud, or genuinely unusual events. Paste a column of numbers below and this tool flags outliers two ways: the Z-score method (how many standard deviations from the mean) and the IQR method (the rule Excel box plots use).
All calculation happens locally in your browser. Your numbers never leave your device.
How outlier detection works
Z-score method: for each value, compute how many standard deviations it is from the mean. Values with an absolute Z-score above a threshold (commonly 3, or 2 for stricter screening) are flagged.
IQR method: sort the data, find the first quartile (Q1) and third quartile (Q3), and compute the interquartile range IQR = Q3 − Q1. Any value below Q1 − 1.5×IQR or above Q3 + 1.5×IQR is an outlier. This is the method behind standard box-and-whisker plots.
What to do with flagged values
Investigate before deleting. An outlier can be a data-entry error (fix it), a valid extreme event (keep it), or a sign your data needs a different model.
For large or multi-column datasets, Excel AI App can scan an entire workbook for anomalies automatically and let you tune the threshold with a slider — no manual copy-paste required.
Frequently asked questions
What counts as an outlier?
Commonly, a value more than 3 standard deviations from the mean (Z-score method) or outside Q1 − 1.5×IQR to Q3 + 1.5×IQR (IQR method). This tool reports both.
Should I use the Z-score or IQR method?
Z-score assumes roughly normally distributed data and is sensitive to extreme values. IQR is more robust for skewed data and small samples. When they disagree, inspect the flagged values manually.
Is my data uploaded anywhere?
No. This outlier finder runs entirely in your browser using JavaScript. Nothing is sent to a server.
Keep exploring
Analyze a whole spreadsheet with AI
Upload an Excel or CSV file and get pivots, outlier detection, and Smart BI dashboards in seconds. Free to start — no credit card.
Open the App Free