Boom! Here’s how a new-age brand decided to stop playing it safe and took their campaign optimization to the next level. Instead of sticking to the standard purchase event, they mastered the Meta Algorithm and smashed all their business goals. Say goodbye to the Shopify CAPI—this brand is setting the standard for what true optimization looks like!

MNMLST’s First Bold Move: Ditching Shopify CAPI

MNMLST, a high-end luxury watch brand, knew that their Meta algorithm needed precise training to accurately target their ideal customer profile. Given the nature of their products, with a relatively low return customer rate, it was crucial to optimize every interaction to achieve their ROAS goals.

Let’s dive into the pivotal moments where we ditched Shopify CAPI to enhance our strategy.

In the first major move, we decided to ditch Shopify CAPI to significantly improve the event match quality—one of the most critical factors in training the Meta algorithm effectively.
(Before and the after image as follows )

The Challenge vs The Goal 

Given the nature of business—a male-dominated luxury watch market and most obvious reasons for low repeat purchase rate with most purchases resulting in regular mid-AOVs —it was clear that strategic adjustments were necessary to achieve growth.

The goals were straightforward: increase higher AOV purchases, attract more female customers, and create hero products across all categories to avoid over-reliance on a single product.

Addressing the elephant in the room – Shopify CAPI the hindrance of all times 

Usually, most brands optimize their campaigns around the standard purchase event, differentiating each campaign primarily through creatives, headlines, and copies

Does Meta algorithm bring in the people by just these elements? 

Standard purchase event –  “Confusion it causes to the algorithm”

Meta AI is a machine learning algorithm which needs to be trained exactly for what the business goal is. And in the recent Meta’s blog post, they had extensively mentioned about how each campaign / adset can be treated as an AI model itself. 

Optimizing the campaign just for purchase events and expecting more women to buy, more shoes to sell, or high AOV buyers to flock—yeah, that’s pure amateur.

However, Meta beautifully explains it can drive your business revenue precisely as you desire! Want to push a specific product line with a higher profit margin? You’ll have complete control.

However, it’s essential to remember that these neural models, with trillions of parameters, require the right AI essentials (first party data) to train effectively. 

Each campaign is an individual model and demands clear goal identification to perform optimally.

Love Shopify but Not Shopify CAPI 🙊

Shopify’s great for building websites, but not for campaign optimization 🙊

Unfortunately, there are limitations in Shopify to create custom conversion events based on the objective goal rather than standard purchase events. 

Let’s dig deeper into the how did MNMLST achieve their goals

The moment: Each campaign is an AI model itself 

We create multiple custom conversion events based on Average Order Value (AOV) and categories like men and women to train the algorithm and maximize conversion value.

The AOV and category based conversion events are as follows:

These custom events allow us to refine the algorithm and focus on securing higher AOV transactions.

The Success moment: When Meta met the Optimization goals 

Each campaign is an AI model itself

This table is a clear proof of concept that when you align your campaign optimization with specific business goals, Meta’s algorithm delivers exactly what you’re aiming for.

For instance, in Campaign 1, the optimization goal was mid_AOV_men. As a result, this campaign achieved the highest percentage of mid_AOV_men purchases compared to others.

Similarly, in Campaign 2, the goal was low_AOV_men, and it delivered exactly that, outperforming other campaigns in attracting low AOV men purchases.

This is the true power of proper algorithm training—it manifests the desired results by precisely targeting the audience you need.

Having the algorithm trained for all kinds of purchases, we have got hero products in every category and scaled up in multiple product level.

Goals we ticked with 1PD OPs

Holistically, we have ticked multiple goals in the due course time which includes; 

1. Training the ad algorithms for multiple categories and improving sales for the same. 
2. Improving the event match quality across the pixels.
3. Create hero products in each product category by targeted conversions  
4. And have seen 117% increase in the revenue in the sense of before and after the 1PD OPs journey.