An outlier is a value that's unusually high or low compared to everything else in your dataset. It might be a data entry error, a measurement mistake, or something genuinely interesting that deserves attention.
Outliers matter because they can skew your averages, distort your charts, and lead to wrong conclusions. A single extreme value in a dataset of 50 rows can throw off your entire analysis.
With small datasets, you might notice an outlier by glancing at the numbers. But when you have hundreds or thousands of rows, manual inspection doesn't work. The unusual values blend in with everything else.
Traditional methods like calculating standard deviations or interquartile ranges require statistical knowledge most people don't have. And even if you can compute them, interpreting the results isn't straightforward.
Queryly analyzes your data and identifies outliers without any manual work. Upload your CSV or Excel file, then ask it to find outliers in any column or metric.
Try prompts like:
Queryly returns a list of outlier values with explanations of why each one is unusual. You get context about what makes it stand out and whether it might indicate a problem or an opportunity.
Queryly doesn't just flag extreme values. It considers the distribution of your entire dataset, looks at patterns across related columns, and provides meaningful explanations instead of just numbers.
The platform also runs a health check on your data when you upload it, which includes outlier detection as part of a broader quality assessment. This gives you a complete picture of your data's condition before you start analyzing.
Finding outliers is only the first step. What you do with them depends on the context:
The goal isn't always to remove outliers. Sometimes they're the most valuable data points in your set.
Try Queryly Free →