Case study

Campaign Analytics for Owned Channel Brand Marketing

How we supported a global retailer to utilise campaign analytics for retaining customers and boosting loyalty throughout the customer journey

Spot types of content resonating most with the different customer segments

Identify the most effective owned marketing channels

Measure the effect along the whole customer journey

The Business Challenge

Our client’s brand marketing teams were lacking insights into the specific target group behaviors and in designing their owned media campaigns they were depending on general customer research and unchecked hypotheses on what content would resonate with the audience. Additionally, they were not tracking consistently the performance of their owned channel campaigns, which was not allowing them to improve continuously. 

Campaign Analytics for Owned Channel Brand Marketing 1
Campaign Analytics for Owned Channel Brand Marketing 2

The Solution

They realized the need to establish a data-driven culture where brand marketing is based on specific data insights and empowers the teams to advance in their learning journey towards increasingly effective own channel marketing.​
​We developed a measurement framework based on the long-term goals of the brand across 5 dimensions along the sales funnel. For every seasonal campaign, we translate its specific goals into KPIs and measure them. In this way, we can determine if the marketing efforts in each season are successful in bringing the brand closer to its longer-term objectives. We collect know-how on which campaign approaches work better than others for the specific target group and steadily improve going forward.
After each campaign, we run analytics measuring the success according to the specific goals and the efforts to fulfill them in the respective season. The measurement covers all stages of the consumer journey. ​

We benchmark these results towards the ones from the previous seasons and measure the continuous success of the brand.

Our Approach

The methods used

Machine learning models were used to achieve the right lead scoring. ​
Decay scores were created for some relevant engagement features: Email sent, Email open, Email click & Page visit. The model doesn’t only count the number of important engagement features but is assigning some scores to the time at which the actions were done. If somebody visits a page today, he/she would be given higher importance than somebody who visited the same page a month back. These decay scores are calculated using an exponential equation.
Decay rates are different for the diverse engagement features: the decay rate for “Email open” is slower than the decay rate for “Email sent”.

ML Model deployment

This machine learning model was deployed successfully on Azure Cloud with no bugs and is being used by the client’s sales team. ​
Amplify pulled data from the client’s marketing applications such as SFDC and Pardot and used the Databricks platform, to train multiple models and MLflow, part of Databricks, to track experiments. ​
The fresh scores are then pushed back to the Salesforce application in an automated fashion.

Business impact

Campaign Analytics allowed the establishment of a data-driven approach when it comes to translating goals into actionable KPIs. This in turn empowered the team to continuously improve their campaigns based on previous performance and historic customer segments’ behaviour. ​More than this, the solution helped to boost engagement and loyalty which translated into better retention and accelerated the customer journey.​​

Related content

Want to know more?

Segmentation / Customer Lifetime Value

Campaign Analytics decodes signals for actionable insights and personalized marketing.