Tags

template marketing
11 Jul 2024 02:09 AM

Identifying and Evaluating Low-Performing Campaigns (AI)

close

In this use case, we have a dataset that comprises lists of advertising campaigns and their daily metrics like marketing spend.

clipboard-2024-07-11-02-07-23-259Z.png

Our goal is to identify and track Ad Campaigns with the lowest performance. Let’s have the AI reformat the sheet, to display days, as separate columns:

clipboard-2024-07-11-02-07-42-891Z.png

Now, our task is to filter the campaigns with 0 conversions in the three days in a row. Click 'Reply' to refine the dataset from Copilot's response and input this prompt
‘Filter the campaigns that have 0 conversions for not less than 3 days’

clipboard-2024-07-11-02-08-17-622Z.png

The final prompt:

Identify campaigns with bad performance.
For every campaign find days when it runs. For every day show Conversions. 
Show days as columns and campaigns as rows. 
Show rows where cells in the dataset is zero at least 3 columns in a row.

Automation capabilities

Now, we aim to optimize this process, enabling AI to automatically check the dataset of interest and notify us about low-performing campaigns via Slack. To achieve this, we would need to create a new Workflow on the corresponding tab:

  1. Drag the 'Ask AI about the dataset' block.
  2. Input the name of the dataset of interest from the Copilot tab.
  3. Drag the 'Create Report / Aggregate' block and choose the source dataset.
  4. Conclude the workflow with either the 'Send CSV to Slack' or 'Send CSV to Email' block.

There you have it – a fully equipped workflow at your fingertips!

Create Copilot Query