Test campaigns using South China Morning Post's ML-driven loyalty prediction algorithm increased engagement by between half and three-quarters, the publisher says.
Vice president of data Korey Lee says the predictive algorithm - dubbed Bluefin after the endangered but loyal tuna which returns to its birthplace to hatch - can optimise marketing campaigns effectively and efficiently.
"We are now starting to use Bluefin to identify new audiences that share characteristics with existing high potential loyal users," he says in an INMA blog post.
In January, the SCMP data team' began a project to understand how readers develop loyalty to specific news outlets and how to nurture that loyalty. "While the ability to predict reader loyalty has many applications, we were interested in using the prediction to optimise our marketing campaigns," he says.
"We used A/B testing with a control group to test whether our predictive engine could improve SCMP's marketing strategy. By focussing on the highest potential readers, we increased engagement with our marketing campaigns and improved the cost efficiency of our marketing."
Loyalty was defined as a multi-session user who returned to the site with a pre-specified frequency and recency.
Of more than 40 variables in the model, those which stood out as top indicators of loyalty were:
Percentage of pageviews in each section;
Time on page;
Duration between the last two visits;
Percentage of sessions on various platforms; and
Percentage of sessions by source and medium.
Using data from June to November 2018, a workflow was built for the algorithm, which began with data extraction. The scoring engine measured the proportion of loyal users that the algorithm correctly predicted and the precision of the algorithm's predictions.
"Each month, we feed the scoring engine back into the data engine to improve the model," says Lee. "This allows the algorithm to learn from the latest data and incorporate any new relevant variables."
Recognising that SCMP readers' consumption patterns vary by region, the team ran the model separately for the US and Asia regions, with multi-month historical data used to perform a cross-time validation on the model's prediction.
"In our multivariate A/B test campaigns in the United States and Asia, we found using the algorithm's predictions increased engagement by 58-78 per cent, and cost effectiveness by 36-52 per cent. This demonstrated that predictive algorithms such as Bluefin can optimise marketing campaigns effectively and efficiently."
He says SCMP is now starting to use Bluefin to identify new audiences that share characteristics with existing high potential loyal users - beneficial not only for maximising marketing budgets, but also creating personalised reader experiences.
"Predictive algorithms such as Bluefin can be used to engage loyal readers in more meaningful ways and minimise reader churn. Predictive algorithms also offer exciting possibilities for engaging with readers in other meaningful ways, which is determined based on a user's preferences and potential."