Found has used the following skills/services in the project.
With 61% of all shopping searches beginning on Google, it's crucial customers can easily find your products in their search results.
If not, simply put, you're missing out on revenue. Revenue you would make if your products were found.
And this was the challenge Secret Sales faced.
Founded in 2020, Secret Sales are a unique marketplace platform that delivers a hugely popular clearance service for designer brands. Through their technological innovation and strong partnerships with designer labels, they aim to become the leading online designer outlet in the UK.
Secret Sales has doubled in size yearly for the last two years and aims to achieve this again in 2022. However, the vast size of their product catalogue made it challenging to surface the right products to customers when advertising.
Our client, Secret Sales were using automated bidding on Google to promote their products to consumers. This is where, Google spends a small amount of the overall budget on each product, sees how well it does and then decides whether or not it's profitable to put more budget behind it.
And here's the problem - when you have the volume of products Secret Sales has, Google Ads' automated bidding technology takes too long to acquire enough data to push new products. Consequently, revenue from new products during their critical initial release period was much lower than it could be, and often missed out on for prolonged periods of time (or even entirely).
As a result, the automated bidding was withdrawing the budget from most products. Which became dormant or 'zombified' – not being bid on and not appearing in any ads.
Profitable products, ready to be found and bought, but customers didn't know they existed, because they weren’t show them in their search results.
So we asked ourselves one question: Could we identify the zombified SKUs - the unique identifiers of each product - surface these in ads to relevant customers and drive incremental revenue for our client?
Spoiler, we could. And here's how.
Our objective was to surface these 'Zombie SKUs' and deliver a 10% increase to the total revenue through Google Ads shopping. Whilst also achieving a return on ad spend (ROAS) that was no lower than existing shopping activity - creating genuine incremental growth from the existing portfolio.
There was no unique target audience as this campaign focused on delivering more inventory to all potential customers. Typically though, our target audience was 20-40 years old.
We started by analysing Secret Sales' historical sales data to study how profitable the different products and variations (size, colour, etc.) had been for Secret Sales. We aimed to predict the gross merchandise value (GMV), the total value of merchandise sold over a given period.
The main challenge we faced was the volume of data that we had to analyse and train a model with. We were working with over 23 million data points from previous product sales.
To overcome this challenge, we leveraged BigQuery machine learning to engineer a deep neural network powerful enough to predict how much GMV a product would generate in a given 30-day period, accurate to within £100. This significantly increased the speed of our model development and the level of complexity that we were able to build into it to achieve the desired level of accuracy.
In other words, we were now able to predict how much revenue could be made from dormant or zombified products by surfacing them through paid ads.
We made our model available to Secret Sales through a secure, easy-to-use web app. This provided:
- Our model was proven to reliably predict the next 30 days of revenue for any individual product (including colour & size variants) to an accuracy of roughly +/- £100. The by-product of this was that we could see under-performing products, tier the scale of their underperformance, and treat them accordingly.
Three separate Shopping campaigns, with unique bid strategies according to the expected potential of the products they contained.
Through a truly innovative approach, including the development of machine learning beyond what even Google can provide at the moment, our work exceeded all expectations.
We aimed to deliver a 10% incremental increase in total revenue through Google Ads shopping and maintain existing ROAS. And so far, we have achieved;
On top of this, the results that we have seen so far are only the beginning. As Secret Sales grows, then the incremental revenue delivered via this approach will also continue to grow – the true benefit of this activity has only just begun.
The effectiveness of this activity has seen it become a fundamental element of our Google Ads activity for Secret Sales. It is now synonymous with new product launches/introductions to market, and our investment in these campaigns has continued to grow.