Back to projects

Customer Journey Analytics & Personalization Engine

Turning fragmented data into actionable retention insights across onboarding, usage, and support touchpoints.

Journey AnalyticsPersonalizationRetentionCLVA/B Testing
Role & Scope

Role: Cross-functional lead across Product, Data, and Client Success

Team: Data engineers, analytics, CS ops, product managers

Goal: Build a 360° journey analytics engine and surface friction points to improve activation, retention, and CLV

Tech Stack
SQLPython (Pandas, NumPy)dbtPower BISalesforceAWS Glue
Outcomes

+18% cross-sell uplift across core segments

+12% improvement in retention

Time-to-insight reduced from 10 days to 1 day

Context

Customer engagement and renewal rates were stagnating. Data across onboarding, product usage, and support was siloed—blocking unified attribution, churn risk visibility, and customer lifetime value tracking.

Approach

Data Model & Integration
  • Designed journey schema linking usage, support, and CRM data (dbt models; AWS Glue jobs).
  • Implemented event tracking & standardized IDs for cross-system joins and cohorting.
Metrics & Analytics
  • Defined Activation %, FCR, NPS correlation, and churn probability as north-star metrics.
  • Built funnel analytics and cohort views in Power BI with Python-based data prep.
Experimentation & Personalization
  • Ran A/B tests for tutorials, nudges, and UI prompts to improve activation & retention.
  • Exposed churn risk and growth levers to execs via automated dashboards and alerting.

Outcome & Impact

Next Steps / Learning

Integrate an ML-based churn predictor and connect to marketing automation to trigger personalized retention campaigns at the right moment in the journey.