Skip to content
English
Contact us
  • There are no suggestions because the search field is empty.

Linear Spend and Impressions Metrics

The current version below is v2. To access the previous version, click here. 

Tatari offers granular TV response data via Tatari S3 buckets. S3 is a secure cloud file-sharing service that allows you to both download raw data and create a script to ingest data automatically, similar to an API. Learn about linear spend and impressions data below.

This article contains the following:

Overview of spend and impressions data

Spend and impressions data allows you to see how much an ad cost, how many people saw it, and how it performed against other spots. Each row in this report shows one spot that aired.

Overview of the files

You’ll have access to two linear spend and impression files via Tatari S3 buckets: 

  • Daily file (immature): This file shows immature data—or the data that we measure before receiving the final spend costs from the network— from the past 45 days*. For example, if the file was created on June 1, 2020, it will contain data from April 17 - June 1, 2020 (the past 45 days). The daily files may have missing or sparse data as we wait for actuals from the networks but will allow you to access immature data until the matured data is available from the monthly files. 
  • Monthly file (mature): This file shows mature data for the previous month*. For example, final spend and impressions data for the month of January would be available March 1st.

*All files are inclusive of data on the broadcast start date and exclusive of data on the broadcast end date. Note that while all datetime values in our reports are in UTC, linear  data is grouped by broadcast time (6am-6am Eastern). So for example, a report with start date 2022-06-01 and end date 2022-07-01 would have datetimes between 2022-06-23 10:00 and 2022-06-24 10:00.

File example

Within the CSV file, you’ll find the following data broken out by spot: 

Column Name

Data Type

Description

spot_datetime

datetime

The date and time in which the spot aired (UTC)

creative_name

string

Creative name

creative_code

string

Creative ISCI (Industry-standard coding identification for commercials)

network

string

Linear network on which the ad was aired

program

string

Program name or null

spend

double

Budget

impressions

integer

Number of people who potentially saw the ad

lift

double

Incremental increase in unique visitors

is_deadzoned

boolean

Whether or not a spot occurs during a deadzone  

spot_id

string

A unique ID of each spot aired; allows you to link to data in other files 

Why does it look like there are duplicate spots?

The spots are actually not duplicates, but rather they're a combination of syndication and spots that have aired close together. Syndications are splintered throughout the country and spots can air very closely together because they are airing on different local providers who manage their own delivery. The spend, impression, and lift are split between them.

How often files are generated

  • Daily file (contains 45 days of data): Every day from 23:00 - 24:00 UTC
  • Monthly file (contains 1 month of data): The first day of the month from 23:00  - 24:00 UTC 

Some examples: 

  • Daily file: If it was created on June 1, 2020, it will contain data from April 17 - June 1, 2020. 
  • Monthly file: Final spend and impressions data for the month of January would be available March 1st. 

All files are inclusive of data on the start date and exclusive of data on the end date.

The measurement attribution type 

All data is incremental attribution.

How to keep reporting up-to-date

To see the most recent data in your internal reporting, you should overwrite any existing data in the date range of the new file while accounting for the UTC to broadcast datetime adjustment (-10/11 hours). We recommend you replace all data from the date ranges in the daily file (45 days immature data) every day once you receive the new file and then again once you receive the monthly (1 month mature data) file.

For example, if you receive a file with dates 2022-05-10 to 2022-06-24 and then the next day you receive a file with dates 2022-05-11 to 2022-06-25, you should delete all data from 2022-05-11 10:00 to 2022-06-25 10:00 and then insert the data from the new file.

You can also refer to our sample python script here, which pulls the report data from our S3 bucket and creates an SQLite3 database locally that you can query. In the script you will find functions that show you how to properly overwrite existing data for initial and daily incremental loads, and thus would be a good reference when building out your own automated process.

Matching Report Data to Dashboard

When trying to match report data to the Tatari dashboard, please be aware that our linear dashboard is split by broadcast time (6am-6am Eastern) and our streaming dashboard is in UTC. When matching our linear reports to the linear dashboard, you would need to convert the datetimes in the reports from UTC to broadcast time (+10/11).

Where to find the reports

In the Tatari S3 bucket under linear_spend_and_impressions/v2, you’ll find daily and monthly CSV files. 

Getting Started: How to access the reports 

Follow the instructions in your dashboard’s AWS Data Sharing page to gain access to your reporting. 

  1. Log in to your dashboard
  2. On the bottom left navigation bar, select “Settings” -> “Integrations”
  3. Select "AWS Data Sharing" from the top navigation bar.