Chozen
User-generated content and social platform
Higher engagement and retention through a behavioural decision engine.
The challenge
Shallow preference signals limited feed relevance and engagement depth.
User-generated platforms struggle to understand preferences deeply enough to drive engagement.
Client
Community and poll-driven social product
Decision type
What to show
The system
Decision system built
We designed a behavioural inference system that models user preferences through interactions and uses that intelligence to personalise content feeds, optimise poll visibility, and match users to relevant content and communities.
System components
Interaction tracking and event pipelines
Interest inference models
Feed ranking logic
Real-time engagement optimisation loops
How we worked
Engagement scope
Behavioural modelling, feed and surface ranking, and instrumentation for continuous learning — integrated with existing content and community features.
Timeline
Incremental rollout of inference and ranking with A/B validation against engagement and retention KPIs.
Operating model
Embedded collaboration with product and data teams; regular review of model drift and community-safety constraints.
Outcomes
Business impact & measurable results
Higher engagement and retention through a behavioural decision engine.
Higher engagement and interaction rates
Stronger user retention through relevance
Self-improving system driven by user behaviour
Governance
Trust, collaboration & governance
Clear documentation of what signals drive personalisation
Escalation paths for moderation and policy alignment
Client team enablement on monitoring and iteration
Reframe
Not a social app — a behavioural decision engine.
Across every engagement, the goal is the same: engineer a system that makes better decisions — faster, more consistently, and at scale — than the process it replaces.
Insights
Related perspectives.
Start a discovery
Most engagements begin with a conversation about context.
We do not send a proposal before we understand the problem. Start by telling us about your decision context — we will identify the highest-leverage intervention areas before any scope is agreed.