AI & Data · EdTech
Converting over 8,000 subscribers with AI-driven prospect modelling
A fast-growing leader in online education
The challenge
What the client was trying to solve
The platform could not tell which users would become loyal paying subscribers, so marketing and discounting were untargeted.
The business problem
- 01
No way to identify the patterns and characteristics of loyal, paying users within a growing student base.
- 02
Marketing and discount strategies could not be personalised at scale.
- 03
Predictive models had to integrate seamlessly into the existing platform to be useful.
Branta's approach
How we worked back from the outcome
A SageMaker prospect model integrated into the platform, with personalised discount recommendations, hosted on AWS with a React Native app.
Analysed student demographics and user behaviour to identify the traits of loyal, high-value users.
Deployed an AI-based prospect modelling system on Amazon SageMaker to predict likely paying subscribers.
Integrated personalised discount recommendations directly into the EdTech platform.
Hosted the platform on AWS and improved the user experience with a React Native application.
Architecture
Problem, thinking, technology, outcome
The system as it runs, from the business problem on the left to the measured result on the right.
- Business problem
Student behaviour data
Demographics and platform usage
- Branta thinking
Amazon SageMaker
Prospect model predicting paying subscribers
- Technology
EdTech platform on AWS
Recommendations integrated into the product
- Technology
React Native app
Personalised discount offers in the user experience
- Measured outcome
Paying subscribers
Over 8,000 converted
Technology
- Amazon SageMaker
- AWS Cloud
- React Native
The outcome
Measured, not described
- 8,000+
- unpaid subscribers converted to paying customers
- More efficient marketing through data-driven, personalised discount strategies.
- A scalable, cloud-based platform ready for the startup’s rapid growth.
What changed
Discounts now go to the users most likely to convert. Over 8,000 unpaid subscribers became paying customers within a short timeframe.
Related success stories
More problems, solved the same way
AI & Data · Beverage
Cutting cooler repair time by 70% with IoT and machine learning
70%
reduction in cooler repair turnaround
AI & Data · Autonomous vehicles
99.9% accurate training data for safer autonomous driving
99.9%
delivery accuracy
Security · Pharmaceutical manufacturing
Enterprise security operations for a pharmaceutical manufacturer in under 12 weeks
< 12 weeks
to a steady operational state
Have a similar problem? Let's solve it.
Tell us what is not working. We will work backwards from the outcome you need to the technology that gets you there.