I turn messy data into actionable insights using a mix of analytics, statistical testing, and automation. Whether it's building dashboards to track business metrics, running hypothesis tests to validate assumptions, or automating repetitive workflows,I focus on solving real problems with data.
Data Analysis & Insights
Exploring data, identifying trends, and translating findings into business recommendations that drive decisions.
Statistical Validation
Using hypothesis testing (t-tests, ANOVA, chi-square) and experimental design to validate assumptions and quantify impact—not just correlations.
Business Intelligence
Building interactive dashboards (Power BI, Tableau) that track KPIs and uncover operational insights.
Automation & Workflows
Streamlining data processes with n8n, Python, and Google Apps Script to eliminate manual work and ensure consistency.
Languages: Python • R • SQL
Visualization: Power BI • Tableau • Looker Studio
Statistical Tools: SPSS • Stata • Hypothesis Testing
Machine Learning: XGBoost • Random Forest • Prophet
Automation: n8n • Google Apps Script
Used Welch's t-test on 17,000+ hours of data to quantify how rain affects service demand. Delivered data-backed staffing recommendations that save £23K/month by optimizing workforce scheduling.
Tech: Python • Hypothesis Testing • Statistical Analysis
Impact: 38.7% demand reduction quantified, dynamic scheduling enabled
Built Power BI dashboard tracking $66M revenue across 4 regions. Automated invoice alerts with Google Apps Script and identified root cause warehouses reducing fulfillment delays.
Tech: SQL • Power BI • Google Apps Script • Automation
Impact: Improved data accuracy, reduced manual reporting time
Analyzed 5,000+ transactions to diagnose 48% product return rate. Used statistical validation to isolate quality issues by variant and recommended fixes projected to increase profit by 23%.
Tech: SQL • Power BI • Root Cause Analysis
Impact: Identified defective product variant, clear action plan delivered
Built ML pipeline predicting telecom customer churn with 85%+ accuracy. Used SMOTE for class balancing and ensemble models (XGBoost, Random Forest) to deliver retention insights.
Tech: Python • XGBoost • Random Forest • Machine Learning
Impact: Identified top 5 churn drivers, enabled targeted retention
Analytics & EDA:
Coffee Shop Customer Behavior (R) • Online Sales Analysis • Demographic Analysis
Business Intelligence Dashboards:
Social Media Ad Performance • E-commerce Superstore • Customer Segmentation
Machine Learning:
Sales Forecasting (Prophet) • Cluster Analysis
Automation:
AI Chat Data Workflow • API Analysis Workflow
I'm open to discussing data projects, analytics challenges, or collaboration opportunities. Currently exploring roles in analytics, experimentation, and business intelligence.
"I believe the best insights come from asking the right questions, testing assumptions with data, and automating what can be automated so you can focus on what actually matters."