Volkswagen Polo: Using Longtail Interest Targeting to Increase Website Visits

16 January 2023

SoMin worked with Volkswagen Taiwan and their media agency, PHD, to find and reach new, high-value audiences while lowering the cost of their Meta campaigns.

Given SoMin's success with the launch of Audi Taiwan's e-tron, when Volkswagen (VW) Taiwan unveiled its brand-new Polo in October 2021, they enlisted SoMin to work with PHD, their incumbent media agency, to boost the performance of its launch campaign on social media.

The challenge:

The goal was to generate excitement for the launch of the Polo despite the challenging market conditions as car sales in Taiwan had begun to decline in Q2 and Q3 and were expected to continue into Q4.

VW needed its campaign to work harder and smarter - reach new customers outside of its typical demographics while minimizing its Cost per Reach (CPM) and Cost per Click (CPC).

Taiwan has been working with their incumbent media agency, PHD, to push for test drives on Meta. Although they had some success generating leads, their cost per link click (CPC) was too high, making it an inefficient use of their marketing budget and lowering their ROI.

This allowed SoMin to help both PHD and Audi through AI-driven optimization solution to further optimize, reduce Audi’s CPC and conserve their marketing budget.

To broaden VW's audience while ensuring that these are high-value customers, we did the following:

  • We used our proprietary Omni-Sourced User Profiling algorithm to gather anonymized audience data from a variety of sources, including VW’s own historical campaign results, the subscribers of their rivals' Meta (Facebook and Instagram) pages, and Google search queries and results. Through this, we were able to analyze more than 225K social accounts across Meta that were associated with the brand and the industry to identify new opportunities to reach our consumers.
  • Our tool then analyzed approximately 2.05 million posts from these accounts using computer vision (CV) and natural language processing (NLP) and collected 4.9 million data points for the collaborative filtering (CF) process.
  • Based on the campaign's objective, SoMin generated 5 campaigns, 299 ad sets, and 871 ads and audiences were clustered based on their likelihood to convert into leads using long-tail targeting.
  • Finally, with Ad Management Automation, all 12 campaigns were managed and optimized automatically every 30 minutes throughout the campaign period.

The results: We effectively managed VW's campaign budget and exceeded all of our KPIs - 29% lower Cost per Impression vs KPI and 62% reduction in Cost per Click vs. KPI.

Furthermore, we were also able to offer machine-observed psychographic insights on VW’s customers, which they could use to guide future creatives and messaging such as their psychological age, psychological relationship status and favorite objects and colors to guide future creatives and messaging.

Download the case study: here

ABOUT THE AUTHOR

Prof. Aleks Farseev PhD

Aleks Farseev is a machine learning wizard who can teach a computer to sing "Bohemian Rhapsody" in binary code. He loves conjuring up new creations and is on a quest to figure out how machine learning can make the world a better place. When not tinkering with technology, Aleks can be found serenading his friends with his accordion skills, which he claims are only slightly less impressive than his machine learning prowess.

Want to have a chat about our products?

We're always happy to talk about how our tools can help people.

Book a Demo