Data sets API

Delivering automatically built data sets to the end-user via REST API.

DATA SETS API delivers automatically built data sets to the end-user via REST API. It accepts any datapoint in a publication as an input, and returns its best matches (i.e. data points with the same meaning and context) in other documents sourced from the same publisher. Utilizing the core of Exerica’s state-of-the-art technology, it provides instant access to the complete data series.

A data point is any number in a pdf, image or HTML document uploaded to the Exerica database. Each data point is assigned a unique ID via a single mouse click on the particular number in the pdf viewer available at our web interface

For example, a click on a number in T-Mobiles US 3Q2020 financial results report (seen in the screenshot below) reveals its ID in the web-link of the browser address bar, and in Exerica’s web interface analytical view on the right-hand side. This ID can consequently be used as an input for DATA SETS API to obtain any other values in the data set which the initial number is part of.



For example, the response to this request would be a data set containing the best matches for the dates appeared in T-Mobile US publications. The response payload would contain the collection of objects with the relevant data point details including (but not limited to) its value and its unique ID identifying it splace in the report. Also provided is a simple web link to instantly open the corresponding publication where the found match is located.


      "value": 196,
      "startDate": "2013Q4",
      "endDate": "2014Q4",
      "durationMonths": 12,
      "company": "T-Mobile US",
      "reportDate": "2015Q4",
      "currency": "USD",
      "scale": null,
      "uid": "005F804BC3DD385A00013CEAC106000BE5C4030838F001",
      "webLink": "",
      "summands": [],
      "confidence": 99

Apart from random data points with provided IDs, DATA SETS API accepts a number of semantic requests to enable access to widely used “Named data sets” (eg “Total assets”, “Net profit”, ”EBITDA” etc).

NB: we can work with any Indo-European languages but Exerica’s Natural Language Processing engine currently delivers the best results in English).

Named data sets enable comparisons across companies, sectors and geographic regions and thereby address the biggest data challenge confronted by decades of financial analysis. Until now the only plausible way to create such global data sets was using manual input by multiple analysts, which generally made it impractical for any real business purpose. DATA SETS API boasts an extensive array of filters enabling users to get the best data match from a specific publication, for specific dates or durations, for a specific scale, or for a specific currency.

Try Data Sets API

In the form below you can try Data Sets API. Use your API Key and preentered data to test Data Set delivery. You can find your API Key in you mailbox after registration. The complete specification of the API is avaliable in the documentation. You can try any of Data Sets API feature with our Swagger.