Attribution modeling accelerator

Overview

Marketers estimate that they waste an average of 26% of their budgets on ineffective channels and strategies, according to a recent study by Rakuten. With increasing pressure on marketing teams to do more with less and increasingly complex customer journeys, our Fractional Attribution Accelerator equips your team with the ability to accurately calculate marketing efficiency.

Our Fractional Attribution utilizes an algorithmic attribution to determine which channels deliver impact and return on ad spend (ROAS) regardless of the conversion type; purchases, form competitions and more. 

What to expect

This accelerator helps you build a deeper understanding of the impact of marketing activity and ROAS spend. It uses the following tools:

• Snowplow – to track events across either your website or single page application
• Snowflake – to house the tracked events
• snowplow_fractribution dbt package and Python script– to model and visualize 

The accelerator takes about ~5.5 hours hours to complete, and includes the following steps:

Step 1. Upload sample data

Use our sample data to create an example atomic and events table within Snowflake. 

Step 2. Model your data

Create your fractional attribution table in your Snowflake warehouse using either our snowplow_fractribution dbt package, Python script or Docker container.

Step 3. Visualize the data

Create a fractibution report table and a graphical representation to see the impact of your channels using our sample data.

Step 4. Set up and deploy tracking

Learn how to implement our web Javascript tracker and test to ensure it is working correctly.

Step 5: Enrich your data

Enrich your data with your existing UTM parameters to populate your analysis. 

Step 6: Modeling your own pipeline

Now that you have set-up tracking and enrichment on your pipeline and generated some test events it is time to make use of what you have learned so far by creating fractional attribution models for your own pipeline data.