Customer Churn Analysis
Python • Power BIIdentify churn drivers and translate predictive insights into retention actions.
- Highest churn: month-to-month
- Risk signals: short tenure + high charges
Open to roles • Manchester, UK • Remote/Hybrid
I turn complex, multi-source data into clear dashboards and actionable insights using SQL, Python, R, Excel, and Power BI.
Featured strengths
A selection of end-to-end analytics work, from data prep to insights and recommendations.
Identify churn drivers and translate predictive insights into retention actions.
Recommend the single campaign to keep under budget constraints to maximise profit and acquisition.
Evaluate profitability, campaign ROI, demographics, and fraud-risk signals.
Segment customers (RFM), compare variants, and surface optimisation opportunities.
Product and customer insights to improve landing-page strategy and segmentation.
End-to-end analysis of drink sales data to identify top-performing products, underperformers, and market trends, supporting data-driven business decisions.
Exploratory data analysis of Alzheimer’s MRI images to assess class distribution, image quality, and dataset readiness for downstream modelling.
End-to-end analysis of UK online retail transactions to uncover customer behaviour, sales patterns, and product relationships.
Synthesise multi-study evidence on nitrogen fertilisation and foliar fungal disease risk.
A toolkit built across analytics, BI reporting, and research.
I am a Data Analyst and Agricultural Scientist with a strong research foundation and hands-on experience building dashboards, segmentation models, and insight-driven reports. I enjoy turning messy datasets into clear narratives that help teams make better decisions, from retention strategy and campaign optimisation to risk monitoring and performance reporting.