Data mapping process occurs automatically during Structured Data ingestion, but you can select fields to map when you create models. 

There are four types of data that Stratifyd treats differently to give users more information. Those data types are:

  • Textual: unstructured textual data, e.g. product review, customer feedback, news article text
  • Temporal: date, time, timestamp 
  • Contributor: name, email, ID, GUID
  • Geographical: location, latitude/longitude, IP address


Textual data is what unsupervised machine learning analyzes to generate buzzwords, a topic model, and sentiment analysis. Depending on the model used, there are various outputs from this data.


The Stratifyd analytics engine normalizes dates by identifying where your temporal data is within your dataset. This provides timelines to display in line graphs or sparklines, and allows you to group data dimensions by:

  • Year
  • Quarter
  • Month
  • Week
  • Day
  • Hour
  • Minute
  • Day of year
  • Day of month
  • Day of week

Temporal data can come into Stratifyd in many different formats.

  • If your data has a field that contains day, month, year, and time in any order, you can select the Date option when you set up the data model.
  • If your date is represented in some other format, select Date and the Stratifyd analytics engine does its best to normalize the data.


Contributor data is used to tie all the insights back to an individual to help organizations close the loop with their customers. The Auto-Topic Predictive Model (Unsupervised NLU) and the User Analysis model use this mapping.

This field is a one-to-one identifier for the creator of the textual data, and maps to the User field.


The Stratifyd analytics engine creates a geographical hierarchy based on the input you provide, giving you access to compare data by country, region, or zip code. The Auto-Topic Predictive Model (Unsupervised NLU) and the Geo Tag model use this mapping.

If your data contains multiple geographical or spatial data points, you can indicate where that data resides when you set up the data model using the following mappings.

  • General
  • Long/Lat
  • Lat/Long
  • Postcode
  • Country
  • State/Province
  • City
  • Street
  • IP Address
  • Phone Number
  • Latitude
  • Longitude

The following geographical fields are absolute, so if you specify one of them, you do not specify country, city, or any other geographical information.

  • Lat/Long field
  • Long/Lat field
  • one Latitude and one Longitude field
  • IP address and phone number

Street, city, state, and country are not absolute, so map as much information as possible if your geographical data takes this form.

Did this answer your question?