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

Linear Spot-Level 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 spot-level data below.

This article contains the following:

Overview of linear spot-level data

Spot-level data shows you the lift associated with your upper funnel (e.g. unique visitors) and lower funnel conversion metrics (e.g. purchases) from linear TV. This report includes both website and install data.

Overview of the files

You’ll have access to two linear spot-level files via Tatari S3 buckets: 

  • 1-day file (mature): This file contains one day’s worth of data* from impressions that occurred 28 days ago. For example, if the file was created on June 1, 2020, it will contain data for May 4, 2020. This data is reconciled and considered mature. 
  • 28-day file (immature): This file contains 28 days’ worth of data* from impressions that occurred 1 day ago up to 29 days ago. For example, if the file was created on June 1, 2020, it will contain data from May 4 - June 1, 2020. The data is unreconciled as it takes 28 days to mature.
    It generally takes 21-28 days for conversions to mature. The 28-day window is an industry standard and is large enough that we can capture most of the conversions related to a spot. It can also take time for us to receive spot level metrics from our data sources.

*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 a breakdown of all the spots:

Column 

Type

Description

spot_id

integer

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

broadcast_week

date

Broadcast week in which the creative aired; the week starts on Monday at 6 a.m. EST

spot_datetime

datetime

Date and time (UTC) when the spot was aired 

creative_name

string

Name of the creative (non-unique)

creative_code

string

ISCI: Industry Standard Coding Identification

network

string

Where the spot aired

rotation

string

When the spot aired during the day

spend

double

Spend associated with a spot

conversion_metric

string

Which metric is being measured (e.g. purchase)

lift

double

Impact of the spot on a given conversion_metric

What does negative lift mean?

Noise from other external factors outside of a viewer seeing a TV ad can outweigh lift on a spot basis, so negative lift i.e. UVs (visitors) minus baseline is possible. Generally, as we aggregate spots the noise becomes less of a factor and you get positive overall lift. 

How often files are generated

Both the 1-day and 28-day files are generated daily between 13:00 - 14:00 UTC.

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 28-day file (immature data) every day once you receive the new one, and then again once you receive the 1-day file (mature data) for each date.

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 S3 bucket under spot_level_metrics/v2, you’ll find unreconciled (immature) and reconciled (mature) reports as 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.