When I first joined the South China Morning Post a little over three years ago, our data team was asked to compile personas with limited resources and no data infrastructure in place.

Eager to help, we cobbled together a report featuring a few user interviews and some demographic data from Google Analytics. But with only a sample of user data and limited behavioural information, the analysis was perhaps more interesting than actionable.

Fast forward to today, and I’m proud to say we’ve come a long way in building up our data infrastructure, while also further enhancing the methodologies that enable us to better understand our readers.

We have employed machine learning to help enhance user profiles, introduced a customer data platform, carried out surveys, quizzes and polls to deepen our understanding of reader preferences and behaviour, and invested heavily in encouraging users to login so we are not wholly reliant on the ever-fleeting cookie.

All these efforts have helped enable us to create “personas”, which will help us better engage with our readers from a marketing perspective, enhance their advertising experience and customise recommendations to improve their interaction with our products.

Personas are representations of who our readers are – an archetypal description and humanistic story around an individual customer that not only illustrates what a reader does or how he or she consumes products, but also why. Good personas provide context about who our readers are, and enable teams to take action to improve engagement.

Rather than group users by geography or pre-defined segments, we wanted to use unsupervised learning to cluster users based on behaviour. To do this, we used k-means clustering algorithms to group our users into cohorts and ran about 40 iterations to observe the optimal turning point in the within-cluster sum of squares (WCSS) – a measure of the variability of the observations within each cluster. More on this here.

This clustering yielded six personas with varying degrees of engagement levels, subscription potential and interests. The size of these clusters also varied substantially.

We then spent several weeks running test campaigns, A/B tests to validate if one cohort outperformed another in the natural tendency to subscribe to newsletters or registered to validate engagement levels and subscription propensity.

We then interviewed dozens of users across each persona to validate the quantitative data with qualitative data. These conversations enabled us to supplement our quantitative assumptions with anecdotes and reader insights into things such as what they wanted to see, and feedback on product improvements, content mix and price sensitivity. Some of the questions we asked included:

• What are our users’ goals and motivations for visiting SCMP?
• How did they find us? Through which touchpoints, channels, or funnels did they come?
• How often do they visit SCMP? What’s their content format preference (bite size, long form, video, podcast, etc)?
• Who are they (age, gender, industry)?
• What types of content (topic, section, content) do they consume?
• Where do they come from (geographically)?
• When do they usually visit SCMP (e.g. what time of day, days of the week etc)?

Here is one of our personas, which we affectionately refer to as the Inquisitive Professional:



As we built these personas over several months, we knew that the most important outcome of this project was to communicate and share these personas across the company and empower various key stakeholders to make these personas actionable and integrate the use of them into our daily workflows.

• Marketing: launch acquisition, retargeting, and retention campaigns to increase user engagement with customised messaging for specific personas
• Product: customise user funnels and experiences per persona so our users can have a more relevant experience, and customise content recommendations for individual personas
• Advertising: enhance personas further with first-party data and provide partners and advertisers with deeper insights into who their potential customers could be, and enable more targeted ads, higher conversion rates, and a more relevant ad experience for our readers
• Editorial: Develop content around specific persona types and collaborate with product to customise experiences

There is still much work to be done on the implementation of such personas, and we are excited to see how they can help us engage more meaningfully with our readers.