How We Reached 60% GMV Increase in 4 weeks Running Programmatic Retargeting Campaign for Home & Shopping
Download the PDF version of the case study
We partnered with Home & Shopping to retarget churned users of their mobile app on Android. With over 10 million downloads, Home & Shopping is one of the most popular e-commerce apps in South Korea.
Results at a Glance
5.4x
outperforming ROAS D1 KPI in week 3
60%
Cohorted GMV increase in 4 weeks
2.3x
GMV per re-engaged user increase within 4 weeks
Campaign Goal
The main goal of the campaign was to reactivate dormant high-value users who had made purchases on the Home & Shopping app in the past and motivate them to make additional in-app purchases to increase Gross Merchandise Value (GMV) and user lifetime value.
The campaign’s performance was evaluated based on a specific D1 ROAS KPI.
Our retargeting campaign with Persona.ly delivered exceptional results from day one, consistently surpassing KPIs and continuing to improve over time. Beyond strong performance, the campaign clearly demonstrated the true potential of retargeting when executed with the right technology and data processing capabilities. It drove significant profit growth, transforming retargeting into a highly efficient revenue engine.
This success has strengthened our partnership, and we’re excited to build on this momentum and unlock even greater impact as we head into the holiday season.
Sunmin Kwon, Manager, Marketing Team, Home & Shopping
Programmatic Retargeting Process
When we launched the campaign for Home & Shopping, using our proprietary Live Audiences segmentation engine, we built segments of high-value users who had previously made purchases in the app but were inactive for a specific period.
Our Live Audiences segmentation engine, available to our clients at no additional cost, integrates natively with our programmatic DSP and our clients’ MMP/CDP of choice.
The direct integration allows us to update audiences in real-time, leveraging live data to efficiently retarget the most relevant audience segments, eliminating the need for third-party
Persona.ly’s Live Audiences segmentation engine in action
tools that require extra investment and process data in batches, causing delays in learning, missing peak intent windows, and resulting in wasted spend.
From the first week of the campaign, we outperformed the ROAS D1 KPI three times.
As the campaign progressed, we gained insights into which audience segments were most likely to return to the app and make additional purchases based on previous in-app behavior.
By slicing and dicing the in-app activity data, we were able to test various audience segments and detect the highest performing combinations, allowing us to bid with maximum accuracy on each individual auction.
As our ML-driven DSP accumulated sufficient data to identify high-conversion audiences, we developed a custom ML targeting model to precisely target high-intent users likely to return and make additional purchases. This enabled precise targeting with value-optimized bidding, resulting in substantial outperformance of the client’s KPI.
As a result, our advanced segmentation, strategic approach, and custom ML-driven targeting capabilities enabled us to achieve D1 ROAS 5.4x above KPI in week 3.
Mobile Programmatic Retargeting Best Practices
Home & Shopping’s campaign results stemmed from an accurate implementation of retargeting best practices.
Exclusive Use of Video Creatives
Home & Shopping deployed exclusively full-screen interstitial video creatives. This format commands full attention by occupying the entire screen, driving measurably higher engagement quality versus traditional banners.
Following each creative rotation, our ML model evaluated the performance of each creative, picked a creative champion in each set, and optimized budget allocation to maximize results.
Deep Linking
Home & Shopping implemented deep linking to reduce user friction and accelerate conversion. Compared to standard tracking links, deep linking directs users to relevant products and personalized offers, significantly improving the performance by minimizing bottlenecks.
Creative Rotation
The Home & Shopping app is renowned for its promotional incentives, welcome offers, and lucky draws. Ad creatives rotation aligns with these promotional cycles, with updated ad sets deployed weekly.
Campaign Results
The Effect of Predicted Age on GMV and CVR
Integrated with all major ad exchanges and processing over 4M ad auctions a second, our bidder weighs multiple factors and processes thousands of combinations of audience characteristics to build a custom targeting model for each campaign.
The initial targeting setup for Home & Shopping included predicted age and gender as pivotal factors driving successful conversion. As the campaign progressed, our programmatic ML-driven bidder identified several conversion patterns.
While gender proved to be trivial, older adult cohorts showed a 22% higher GMV per user and conversion rate from re-attribution to purchase compared to other age-based segments.
Application of Value-Optimized Bidding to Drive GMV Growth
Our ML algorithm identified and factored previous purchase history to be a strong conversion predictor. Frequent shoppers cohort outperformed one-time shoppers by 5x, and retargeting the top spenders yielded the most dramatic results, outperforming the ROAS KPI 10x.
Leveraging these insights, our ML-driven bidder dynamically optimized bidding toward high-intent cohorts. This enabled precise retargeting in real-time, capturing users at peak intent and driving substantial budget efficiency gains through instant ML optimization.
Utilizing value-optimized bidding, our campaign for Home & Shopping achieved a 2.3x GMV per re-engaged user and 1.6x GMV growth without additional investment.
About Home & Shopping
Home & Shopping is one of Korea’s leading e-commerce platforms specializing in TV home shopping and mobile commerce. Established in 2011 to expand sales channels for small and medium-sized enterprises, the platform connects consumers with locally-produced goods through integrated broadcast and digital channels.
Our partnership with Home & Shopping has been outstanding.
By leveraging our advanced ML capabilities and tailored strategy, we delivered unprecedented results.
We’re proud to see our ML-driven DSP perform across verticals, including e-commerce, and remain committed to expanding our footprint in the Korean market while providing leading programmatic DSP solution to local advertisers.
Shana Kim – Business Director, APAC at Persona.ly
About Persona.ly
Persona.ly is a data-driven product company specializing in mobile user acquisition and retargeting, powered by proprietary machine learning algorithms and a robust first-party data management platform.
We help leading mobile companies including King, Tencent, Papaya, NextNinja, Tilting Point, Nexon and many others reach and exceed their growth goals by accurately predicting which users are most likely to engage and convert. Our machine learning models are optimized to target high-value users based on predicted LTV, driving strong ROAS and long-term user quality.
Our in-house programmatic DSP is directly integrated with top-tier ad exchanges and OEMs, processing over 4 million ad requests per second globally.
By combining real-time predictive analytics with programmatic scale, we empower our partners to unlock smarter growth, higher LTV, and measurable incremental impact.
Thank you for your interest!
Our team will get in touch with you shortly.
