Staff Reporters
Apr 27, 2021

How Alodokter lifted engagement by 45% using machine learning

CASE STUDY: The healthcare superapp used MoEngage's machine-learning technology and A/B testing mechanism to keep users active and engaged, even when they're not unwell.

How Alodokter lifted engagement by 45% using machine learning

Background and objective

Indonesian healthcare superapp Alodokter provides end-to-end digital solutions to patients including telemedicine, doctor bookings, medical content, and health-insurance services. It has more than 28 million monthly active users, and more than 40,000 certified doctors on the platform.

Perhaps unsurprisingly, Alodokter found that engagement was high when users were unwell, but that it was difficult to keep people active on the app otherwise. It also found that it had a retention problem, with a lot of uninstalls happening almost immediately after installation.

Alodokter’s marketing goals were three-fold: increase app engagement to reduce churn and boost retention, increase active users across the app, and improve conversion and clickthrough rates
(CVRs and CTRs) of push campaigns to uplift engagement.

Alodokter wished to keep users engaged by providing insights and information about health and safety,
precautions, and illness prevention at the most appropriate times.

Execution

Alodokter partnered with MoEngage to apply its AI-enabled content optimisation feature, known as Sherpa, and A/B testing mechanism to run MoEngage’s proprietary Flows campaigns. Flows is a series of cross-channel lifecycle campaigns that are sent to customers based on their on-site or in-app activity.

To better target the audience, MoEngage helped Alodokter map out user journeys based on variables such as location, preferences, attributes, conversion events, and funnel drop-offs. Then, to boost the performance of the Flows campaigns, MoEngage helped personalise the call-to-action based on the stage of the customer journey. 

For example, if the user had signed up they were encouraged to perform a conversion event. After the first conversion, the goal is for users to perform more conversions over the duration of the campaign. MoEngage’s Sherpa selected the right communication approach for the Flows campaigns by measuring and optimising the content at each stage of the journey. The campaigns were designed to engage existing users, re-engage inactive users and improve conversion. 

Results

With support from MoEngage’s Sherpa, Alodokter’s marketing team was able to reduce churn and increase CTRs and CVRs, increase app engagement and re-engage inactive users. Overall, Alodokter saw the following results:

  • 6% to 16% CTR improvement to activate users who had signed up.
  • 5% to 10% CTR improvement to turn free-chat users into premium-chat users.
  • 10% to 12% increase in funnel conversion rate from user onboarding campaigns.
  • 60% increase in MAUs in eight months between February and October 2020.
  • 45% uplift in engagement from push campaigns in August to September 2020.

In addition, Alodokter used Sherpa to float a survey to users to find out what people would like to obtain from its new e-pharmacy feature AloShop, resulting in a significant uplift. The CTR improvement in the e-pharmacy survey campaigns was 19% for iOS devices and 40% for Android devices.

Source:
Campaign Asia

Related Articles

Just Published

4 hours ago

Havas warns of ‘reputational’ risk from fossil-fuel ...

The Vivendi-owned agency group made the disclosure in its stock market prospectus.

4 hours ago

MediaSense buys R3 as it eyes global client ...

Combined business will work for brands who spend more than $60 billion on marketing and media investment.

12 hours ago

40 Under 40 2024: Hai Anh Vu, Publicis Media

Vu’s rapid and assured changes upon joining Publicis resulted in positive transformation across business and talent in just two years.

14 hours ago

BWS’ new ad says 'take your time'—even if you’re ...

BMF’s latest campaign for the Aussie beverage giant features a procrastinating partygoer who hilariously proves that 'on my way' can mean anything but.