Exacaster Analytics API

Get rich time series insights with a single API call

TRY IT FREE VIEW EXAMPLE
Outliers & Changes
Outliers & Changes
Detect multiple outliers and change points in your time series.
Outliers and Change Detection
Time Series Description
Analyse the content of the time series and assign meaningful descriptions to subsets of time series.
Outliers and Change Detection
Time Series Forecasts
Get time series forecasts powered by state of the art AI algorithms.

Try Exacaster Analytics API

Paste your time series or take a look at predefined examples by clicking Shuffle symbol.
Like what You see? TRY IT FREE
Outliers & Changes

Outliers and Change Detection


Outlier detection algorithms spot abnormal behaviour in your time series (e.g. sales on Mondays used to be $100k and this Monday it's $150k ) and make sure that only meaningful outliers would be reported, so that you would not be bothered with false alerts.

Change detection algorithms analyze the patterns of your time series, searches for changes in the underlying process and alerts when a important change was found (e.g. sales used to be stable and now started decreasing, the moment when sales started decreasing will be alerted as a change point).

Outlier and change detection are useful for monitoring use cases such as: ETL (processing time, table partition size, rows count, etc.), infrastructure monitoring (CPU and RAM load, processed requests, etc.), sales (numbers of product purchases over time), fraud detection etc.

Time Series Description


Description algorithms analyze label each part of time series with multiple characteristics such as: seasonality period, shape (increasing/decreasing/flat ranges, step-up/step-down points, etc.) They use a unique deep learning approach based on visual recognition of patterns - just like a real data analyst would do.

The amount of different labels is constantly increasing and labelling accuracy is improving over time as more and more cases are introduced.

This is particularly useful for automated text report generation and next generation analytical approaches as it enables a specific time series pattern search e.g. select all product sales that have been increasing for a while and are now flat.

Video
Time series prediction

Time Series Forecasts


Our powerful time series prediction algorithms allow to make forecasts with a state of the art prediction accuracy. The algorithms are designed to learn from the data, capturing seasonality, periods, linear and non-linear trends, characteristics of randomness. The various components that make up the time series are then combined in a way to make a very robust forecast, which displays not only the general trend, but also the randomness properties.

Time series predictions are extremely useful for planning challenges (e.g.: what will my sales be in Q2? What storage capacity will I need in the next month? etc.)

Pricing


First 1000
API calls / month
Outlier
Free
Change
Free
Period
Free
Labels
Free
Prediction
Free
Chart
Free
All
Free
1000 - 1 mln.
API calls / month
Outlier
$1.50 per 1000 API calls
Change
$1.50 per 1000 API calls
Period
$1.50 per 1000 API calls
Labels
$1.50 per 1000 API calls
Prediction
$3.00 per 1000 API calls
Chart
$4.00 per 1000 API calls
All
$4.00 per 1000 API calls
< 1 mln.
API calls / month
Outlier
$1.00 per 1000 API calls
Change
$1.00 per 1000 API calls
Period
$1.00 per 1000 API calls
Labels
$1.00 per 1000 API calls
Prediction
$2.00 per 1000 API calls
Chart
$2.50 per 1000 API calls
All
$2.50 per 1000 API calls
E.g. First (any type) 1000 API calls per month are free, 1 001 to 999 999 calls are charged $1.50, above 1 mln. - $1.00
Ready to get started?Get in touch or try it free CONTACT SALES TRY IT FREE

Contact us to get free access