Skip to content

Data Specification

The Alvíss AI – Commercial Navigator (CN) application has a set of
strict requirements on the types of data it can work with. This document
will run through the file formats, conventions, and assumptions that
this application is operating under. The application supports models,
data, and insights on a granular level.

  • Commercial Navigator is a flexible platform that allows you to add the data sources you need for your specific business
  • We support Sales, Price, Media, Brand, Visits, Events and Macro data out of the box
  • Each of these data sources need to adhere to a specification in order for the platform to understand them
  • While it’s possible and recommended to add all the data sources you can get your hands on, the only requirement is “Sales”
  • This means you can start out simple and move to a more complex setup

Data explanation

The CN app needs a number of datasets to function properly. The main
datasets supported are

  • Sales: The most important file, and actually the only one required, is the
    Sales data file. It contains the number of units sold and the price the
    consumer paid for it
  • Distribution: Contains information about distribution like number of stores, sales agents, offices etc
  • Brand: Information about your brand like awareness, liking, penetration, consideration etc. This is also where CX related tracking goes.
  • Events: This captures all kinds of events which extends over a given period of time. Could be events like Force Majeure or other extraordinary events.
  • Visits: This is information about footfall in stores or visits to a website or anything else that counts as some kind of traffic.
  • Macro: This data type supports all kinds of macroeconomic data like unemployment rate, consumer confidence, consumer price index, interest rates and currency exchange
  • Media: Media investments and media groupings for all media related impressions and campaigns

Note

These datasets have a specific File Format that needs to be adhered to in order for the application to understand them.

Note

The data sources needs to have a coherent data Periodicity meaning that the values need to be observed and registered in the same interval.