MMM Case Study: +13% in Conversions with the Same Budget

The Question

If I have 14 campaign types in my Marketing Mix, how much should I spend on each channel to maximize my return?

The Brand

The company sells shipping for eCommerce businesses. It allows eCommerce businesses to buy cheap shipping that delivers better service for the end client compared to other shipping suppliers in Italy.

The Challenge

As a business born during COVID, the company experienced incredible growth that led to more than doubling its marketing investments. From investing only in Google Search, it expanded to Facebook, programmatic, Bing, YouTube, Display, Performance Max, and more.

After multiple conversion lift experiments, the team noticed that attribution was broken: 60% of conversions went into a "Direct" source.

The Problem

How can you plan your advertising budget if you can't know what ROI each channel actually generated in the past?

How can you better allocate your advertising budget to experience incremental sales?

The Solution

The marketing team leveraged Cassandra MMM to evaluate the performance of past investments and discover the real ROI of each channel.

Beyond historical attribution, Cassandra analyzed and modeled diminishing returns curves for all advertising channels. These curves told the marketing team the breaking point at which each investment started to become inefficient.

After the initial analysis, the marketing team used the Cassandra Budget Allocation tool to validate their budget distribution hypothesis. They asked the model to predict the optimal spend per channel for the next two weeks. The model recommended reducing the Meta advertising budget and reallocating it to Google Search and Google Video.

This new allocation was projected to increase conversions by 5.5% compared to the previous period.

The distribution was implemented.

The Results

After two weeks, the team measured the results.

They experienced a 5.75% increase in the number of conversions compared to the previous period.

Cassandra then refreshed its model on the new data and generated a new budget allocation for the following two weeks. The recommendation:

"Lower your budget by 12% on Google Search ads and reallocate 8% to Google Discovery and 4% to Meta."

This change was projected to increase total transactions by 6.6%.

The distribution was implemented.

After another two weeks, the team saw a +7.6% increase in the number of transactions.

Summary of Results

In one month and one week, by modifying budget distribution only — no increase in total spend — the brand achieved:

• +13.36% in the number of transactions

• +42.21% in profit

• +22% in ROAS

• -7% CAC (thanks to an additional Geo-lift experiment)

How to Implement This in Your Organization

Cassandra's approach consists of three steps:

Step 1: In 2 weeks you receive a personalized MMM for your company, with a money-back guarantee if you don't like the outcome.

Step 2: In 2 weeks we build a data infrastructure to centralize all your data daily and refresh the model every two weeks.

Step 3: 2 hours of monthly consultancy to transform model insights into experiments that will drive better ROI over time.

Try Cassandra for free or book a demo to see if and how we can help you.