Categories

← View All Tools

Time Series Anomaly Detector

Upload CSV or JSON time series data, detect anomalies with Z-Score and IQR methods, and return a chart-backed report

Example Results

2 examples

Flag a suspicious spike in daily revenue

Upload a simple time series and highlight an outlier day with a chart and anomaly segment summary

Time series report with one highlighted anomaly and a rendered chart.
View input parameters
{ "rawInput": "timestamp,value\n2026-03-01,110\n2026-03-02,112\n2026-03-03,109\n2026-03-04,315\n2026-03-05,111", "timestampColumn": "timestamp", "valueColumn": "value", "detectionMethod": "both", "zScoreThreshold": 2.5, "seasonalityWindow": 0 }

Review server latency drift with seasonal context

Analyze monitoring data with Z-Score and a seasonality window to separate ordinary fluctuations from real incidents

Time series report with anomaly markers, trend slope, and contiguous anomaly segments.
View input parameters
{ "rawInput": "timestamp,value\n2026-03-01T00:00:00Z,122\n2026-03-01T01:00:00Z,121\n2026-03-01T02:00:00Z,119\n2026-03-01T03:00:00Z,165\n2026-03-01T04:00:00Z,120\n2026-03-01T05:00:00Z,118", "timestampColumn": "timestamp", "valueColumn": "value", "detectionMethod": "zscore", "zScoreThreshold": 2, "seasonalityWindow": 3 }

Click to upload file or drag and drop file here

Maximum file size: 25MB Supported formats: text/csv, application/json, application/vnd.ms-excel, application/vnd.openxmlformats-officedocument.spreadsheetml.sheet

Key Facts

Category
Data Analysis
Input Types
textarea, file, text, select, number
Output Type
html
Sample Coverage
4
API Ready
Yes

Overview

The Time Series Anomaly Detector is a powerful utility that analyzes CSV or JSON data to identify unusual spikes, drops, or outliers. By applying statistical methods like Z-Score and Interquartile Range (IQR), it automatically flags anomalies and generates a visual HTML report with a rendered chart, making it easy to spot irregular trends in your data.

When to Use

  • •When you need to quickly identify abnormal spikes or drops in daily metrics like revenue, traffic, or active users.
  • •When analyzing server logs or monitoring data to pinpoint latency issues or downtime events.
  • •When cleaning historical datasets to remove or investigate statistical outliers before training machine learning models.

How It Works

  • •Upload your time series data as a CSV, JSON, or Excel file, or paste it directly into the text area.
  • •Specify the column names for your timestamps and values, then select your preferred detection method (Z-Score, IQR, or both).
  • •Adjust the Z-Score threshold and seasonality window to fine-tune the sensitivity of the anomaly detection.
  • •Generate a comprehensive HTML report featuring an interactive chart and a summary of all flagged anomaly segments.

Use Cases

E-commerce managers tracking daily sales to detect unexpected revenue drops or viral product spikes.
DevOps engineers monitoring server CPU usage and latency to identify infrastructure bottlenecks.
Financial analysts reviewing daily stock prices or transaction volumes to spot irregular trading activities.

Examples

1. Flagging a Suspicious Revenue Spike

E-commerce Analyst
Background
An analyst is reviewing daily revenue data and notices an unusually high total for a specific week.
Problem
Needs to mathematically confirm which specific day is a statistical outlier compared to the rest of the week.
How to Use
Paste the daily revenue CSV data, set the timestamp and value columns, and select 'Z-Score + IQR' as the detection method.
Example Config
Detection Method: Z-Score + IQR, Z-Score Threshold: 2.5, Seasonality Window: 0
Outcome
The tool generates a chart highlighting the exact day the revenue spiked to 315, confirming it as a statistical anomaly.

2. Reviewing Server Latency Drift

DevOps Engineer
Background
A DevOps engineer is investigating intermittent slow response times on a web server.
Problem
Needs to separate ordinary traffic fluctuations from actual latency incidents using hourly monitoring data.
How to Use
Upload the server latency logs, select the Z-Score method, and apply a seasonality window to account for normal traffic patterns.
Example Config
Detection Method: Z-Score, Z-Score Threshold: 2, Seasonality Window: 3
Outcome
The HTML report visualizes the latency trend and flags the 165ms spike at 03:00 as a true anomaly, ignoring minor fluctuations.

Try with Samples

json, csv, xml
CSV Samples
Sample CSV files with various data types, sizes, and complexity levels
preferred input family json,csv
json, csv
Python Samples
Essential Python code examples and Hello World demonstrations
preferred input family json,csv
json, csv
XLSX Samples
Sample XLSX spreadsheets for worksheet parsing and data extraction testing
preferred input family xls,xlsx
xls, xlsx
WebRTC Real-Time Communication Samples
Comprehensive WebRTC samples for peer-to-peer audio/video communication, data channels, screen sharing, and signaling server implementation
title token time
json

Related Hubs

Json Tools
Explore 44 json tools for utility workflows and compare closely related utilities quickly.
Json Convert Tools
Explore 100 json tools for convert workflows and compare closely related utilities quickly.
Text Convert Tools
Explore 80 text tools for convert workflows and compare closely related utilities quickly.
Csv Convert Tools
Explore 37 csv tools for convert workflows and compare closely related utilities quickly.

FAQ

What data formats are supported?

You can upload CSV, JSON, or Excel files, or paste raw CSV/JSON text directly into the input field.

What is the difference between Z-Score and IQR?

Z-Score measures how many standard deviations a data point is from the mean, which is great for normally distributed data. IQR uses quartiles to find outliers and is more robust against extreme values.

How does the seasonality window work?

The seasonality window allows the tool to account for recurring patterns over a specified number of periods, helping to separate normal seasonal fluctuations from true anomalies.

Can I customize the sensitivity of the detection?

Yes, you can adjust the Z-Score threshold between 1 and 6. A lower threshold flags more points as anomalies, while a higher threshold only flags extreme outliers.

What does the output report include?

The tool generates an HTML report containing a visual chart of your time series, highlighted anomaly markers, trend slopes, and a summary of contiguous anomaly segments.

API Documentation

Request Endpoint

POST /en/api/tools/time-series-anomaly-detector

Request Parameters

Parameter Name Type Required Description
rawInput textarea No -
dataFile file (Upload required) No -
timestampColumn text No -
valueColumn text No -
detectionMethod select No -
zScoreThreshold number No -
seasonalityWindow number No -

File type parameters need to be uploaded first via POST /upload/time-series-anomaly-detector to get filePath, then pass filePath to the corresponding file field.

Response Format

{
  "result": "
Processed HTML content
",
  "error": "Error message (optional)",
  "message": "Notification message (optional)",
  "metadata": {
    "key": "value"
  }
}
HTML: HTML

AI MCP Documentation

Add this tool to your MCP server configuration: 

{
  "mcpServers": {
    "elysiatools-time-series-anomaly-detector": {
      "name": "time-series-anomaly-detector",
      "description": "Upload CSV or JSON time series data, detect anomalies with Z-Score and IQR methods, and return a chart-backed report",
      "baseUrl": "https://elysiatools.com/mcp/sse?toolId=time-series-anomaly-detector",
      "command": "",
      "args": [],
      "env": {},
      "isActive": true,
      "type": "sse"
    }
  }
}

You can chain multiple tools, e.g.: `https://elysiatools.com/mcp/sse?toolId=png-to-webp,jpg-to-webp,gif-to-webp`, max 20 tools.

Supports URL file links or Base64 encoding for file parameters.

If you encounter any issues, please contact us at [email protected]