Natnael Amenu

<p>The findings reveal that while revenue remains stable over time, the business is largely unprofitable across most categories and regions. Losses are primarily driven by specific product categories and geographic markets. The analysis provides actionable recommendations to improve pricing strategies, optimize product focus, and enhance profitability.</p><h2><strong>Business Problem</strong></h2><p>The company relies on sales data to monitor performance and support strategic decisions. However, inconsistencies and data quality issues reduce the reliability of insights.</p><p>Additionally, despite strong revenue performance, the company struggles with profitability. This raises key business questions:</p><p>Why is the business not profitable despite high sales? Which products and regions are driving losses? How can the company improve margins and decision-making?</p><p>This project aims to clean the data, uncover key performance drivers, and provide actionable business recommendations.</p><h2><strong>Methodology</strong></h2><p>The analysis followed a structured data analytics workflow:</p><p>Data Cleaning &amp; Validation Handled missing values and duplicates Standardized categorical variables (e.g., regions) Corrected data inconsistencies (e.g., negative sales values) Exploratory Data Analysis (EDA) Time-series analysis (monthly sales trends) Aggregation by category, region, and customer Profitability Analysis Computed profit margins Identified loss-making segments Segmentation Analysis Category-level performance Region-level performance Customer-level profitability</p><h2><strong>Skills &amp; Tools</strong></h2><p>Programming &amp; Analysis Python pandas → data cleaning, transformation, aggregation matplotlib → data visualization numpy → numerical operations Data Analysis Techniques Data cleaning &amp; preprocessing Exploratory Data Analysis (EDA) Aggregation &amp; grouping Time-series analysis Profitability and margin analysis Tools Jupyter Notebook GitHub (project version control &amp; documentation)</p><h2><strong>Results &amp; Business Recommendations</strong></h2><h3><strong>Key Findings</strong></h3><p>Revenue vs Profit Disconnect High-revenue categories (Furniture, Technology) are unprofitable Office Supplies is the only consistently profitable category Regional Performance Issues USA generates strong sales but the largest losses Europe is closest to break-even Seasonality &amp; Volatility Sales show seasonal peaks (March, July, October) No strong long-term growth trend Customer Profitability Gaps Some high-revenue customers generate negative profit Business Recommendations Optimize Pricing &amp; Costs Review pricing strategies for Furniture and Technology Reduce costs in loss-making segments Focus on Profitable Segments Scale Office Supplies, especially in Europe and Asia Improve Regional Efficiency Investigate operational inefficiencies in the USA market Customer Strategy Optimization Reassess unprofitable high-revenue customers Leverage Seasonal Trends Replicate successful strategies from peak months</p>

This project analyzes retail sales data to identify key drivers of revenue and profitability. The dataset contained multiple data quality issues (missing values, inconsistent categories, incorrect entries), which were cleaned and standardized before analysis.

Python

pandas

Data Analysis

This project demonstrates the ability to:

Clean and structure messy real-world data Translate data into business insights Provide actionable, stakeholder-focused recommendations

Sales Data Quality Audit & Profitability Analysis for Retail Business

<p>The analysis reveals a high overall churn rate (52%), particularly concentrated in lower-tier plans and monthly subscriptions. While enterprise customers generate significantly higher lifetime value, entry-level plans show weak retention and low profitability.</p><p>Key recommendations include improving pricing strategy, incentivizing annual billing, and targeting high-value customer segments to improve retention and long-term revenue.</p><h2><strong>BUSINESS PROBLEM</strong></h2><p>CloudTask Pro is experiencing strong customer growth but faces a critical issue: high churn. Leadership needs to understand whether the company is growing sustainably or simply replacing lost customers.</p><p>The key questions addressed in this analysis are:</p><p>Which customers are most likely to churn? What are the main drivers of churn? Are all customer segments equally profitable? How do churn and acquisition impact long-term revenue?</p><h2><strong>METHODOLOGY</strong></h2><p>Exploratory data analysis using SQL to validate data quality and structure Churn rate analysis across multiple dimensions (plan, billing cycle, company size, acquisition channel) Revenue trend analysis using monthly MRR and net customer growth Unit economics modeling (CLV, CAC, CLV:CAC ratio) Behavioral analysis using feature usage and NPS to identify at-risk customers Interactive dashboard built in Power BI for visualization and stakeholder insights</p><h2><strong>SKILLS (this is VERY important)</strong></h2><h3><strong>Tools &amp; Technologies</strong></h3><p>SQL Server (data querying and aggregation) Power BI (dashboard development, DAX measures, data modeling) Excel (initial data validation and exploration)</p><p>SQL</p><p>GROUP BY aggregations CASE WHEN logic for churn calculations Window-style analysis for segmentation Data cleaning and validation queries</p><p>Power BI / DAX</p><p>KPI measures (MRR, churn rate, CLV, CAC) Calculated columns (At-risk segmentation) Measures using AVERAGE, DIVIDE, CALCULATE Data modeling across multiple tables Interactive dashboard design with slicers and filters</p><p>Business Concepts</p><p>Customer Churn Analysis Monthly Recurring Revenue (MRR) Customer Lifetime Value (CLV) Customer Acquisition Cost (CAC) Net Revenue Retention Customer Segmentation</p><h2><strong>RESULTS &amp; BUSINESS RECOMMENDATIONS (MOST IMPORTANT)</strong></h2><h3><strong>Key Findings:</strong></h3><ul><li><p>High overall churn (52%) indicates significant retention issues</p></li><li><p>Starter plan has the highest churn (70%), suggesting weak product-market fit or pricing mismatch</p></li><li><p>Monthly subscriptions churn significantly more (60%) than annual plans (40%), highlighting billing structure as a key driver</p></li><li><p>Top churn drivers are Budget Cuts, Price Sensitivity, and Company Closures</p></li><li><p>Enterprise customers generate the highest CLV ($13.5K), while Starter customers contribute minimal long-term value ($300)</p></li><li><p>CLV:CAC ratio varies significantly, with Enterprise being highly profitable and Starter barely covering acquisition cost</p></li><li><p>Over 65% of customers are flagged as at-risk, based on low feature usage and low NPS</p></li></ul><h3><strong>Business Recommendations</strong></h3><p>Shift focus toward high-value segments (Enterprise &amp; Business) to maximize profitability Encourage annual billing through discounts or incentives to improve retention Re-evaluate Starter plan pricing and value proposition to reduce churn Improve onboarding and feature adoption, as low usage strongly correlates with churn Target retention strategies for at-risk customers using usage and NPS signals Optimize acquisition channels to focus on higher-retention customer segments</p><div class="image-container"><div class="image-row-wrapper"><div class="image-wrapper"><img src="https://cdn.collective.work/cmor3bkit4d3n42co3pek08gk.png"><div class="image-overlay"></div></div></div></div><div class="image-container"><div class="image-row-wrapper"><div class="image-wrapper"><img src="https://cdn.collective.work/cmor3b54g4cim3xeyfmqn9x0s.png"><div class="image-overlay"></div></div></div></div>

This project analyzes customer churn, revenue trends, and unit economics for a B2B SaaS company. The goal was to identify the drivers of high churn, evaluate customer profitability, and highlight opportunities for sustainable revenue growth.

SQL Queries

Data Visualization

Incorporate cohort analysis to better understand retention over time Track product usage at a more granular feature level Build predictive churn models using machine learning Improve data granularity for revenue (e.g., expansion MRR, contraction MRR) Validate assumptions with real business data and customer feedback

SaaS Revenue Churn Unit-Economics Analysis

Alteryx Designer Core Certified

Excel for Financial Planning and Analysis (FP&A)

KPMG UK - Audit Job Simulation

Data Analysis Fundamentals

PwC Switzerland - Power BI Job Simulation

GitHub

datascienceportfol.io

Junior Data/BI Analyst

– Excelled in analytical and problem-solving
– Working effectively with team members and clients from diverse backgrounds.
– Interacting with client to understand their needs and provide tailored solutions.

Natnael Berhanu Amenu

Junior Data/BI Analyst

About me

Work experience

Consultant (Global Consulting Program)

Jr. System support

Salesperson

Education

Burgundy School of Business - BSB

Burgundy School of Business - BSB

Addis Ababa University

Licenses & certifications

Alteryx Designer Core Certified

Excel for Financial Planning and Analysis (FP&A)

KPMG UK - Audit Job Simulation

Data Analysis Fundamentals

PwC Switzerland - Power BI Job Simulation

Portfolio

Sales Data Quality Audit & Profitability Analysis for Retail Business

Natnael Amenu

SaaS Revenue Churn Unit-Economics Analysis

Natnael Amenu

Talents

Recruiters

About