← Back to Portfolio
Project 01 — E-Commerce Performance

Segment, Retain, Grow: Sales Analysis to Boost E-Commerce Revenue

Customer segmentation · Cohort analysis · Churn prediction · RFM modelling

+18%
Projected CLV uplift
34%
Churn rate reduction
8,400
Customers analysed
4
Actionable segments
Python (pandas, scikit-learn)
SQL
Tableau
RFM Analysis
K-means Clustering
Logistic Regression
Project Narrative

From data to
retention strategy.

Problem
Revenue stagnation despite growing acquisition spend. High one-time purchase rate with low customer lifetime value across all cohorts. The business had no visibility into which customers were worth investing in.
Data
12 months of transactional data across 8,400 customers. SQL queries on order history, return rates, and session frequency. Data cleaned and structured via Python pandas pipelines.
Solution
RFM segmentation (Recency, Frequency, Monetary) applied in Python. K-means clustering confirmed four actionable customer tiers. Results visualised in an interactive Tableau dashboard.
Recommendation
Priority retention programme for the "at-risk champions" cluster, representing 23% of customers but 41% of revenue. Personalised email sequences and tiered loyalty incentives proposed by segment.
Impact
Projected 18% increase in 6-month CLV for the reactivated segment. Predicted 34% reduction in churn for the high-value cohort, validated at 95% confidence with a holdout test group.
Method
K-means clustering for segmentation, logistic regression for churn prediction, cohort analysis for retention curves. Every result statistically validated before recommendation.
Data Visualisation

The numbers
behind the decisions.

RFM Customer Segmentation
Distribution of 8,400 customers across four actionable tiers
Revenue Contribution by Segment
Share of total annual revenue per customer tier
Monthly Retention Curves by Cohort
Customer retention rate over 12 months for Champions vs At-Risk segment, before and after intervention
Churn Probability Distribution
Logistic regression output across customer base (% at risk per bin)
Projected CLV Impact by Segment
6-month customer lifetime value before and after retention strategy
Tools & Methods
Python (pandas) scikit-learn SQL Tableau RFM Analysis K-means Clustering Logistic Regression Cohort Analysis A/B Testing Statistical Significance Testing

"The highest-value customers were invisible inside aggregate revenue figures. Segmentation made them actionable."

Next: Project 02 →