Data Analyst • DevOps Engineer • Analytics Nerd with a Human Touch
🚀 I transform messy datasets into actionable insights and automate manual chaos with scalable tools.
From building lead-scoring models and MMM frameworks to deploying AI bots and Slack-integrated dashboards — I operate where data, strategy, and systems meet.
Currently finishing my Master’s in Business Analytics at UC Davis, I bring 5+ years of global experience spanning refineries, notaries, and neural nets. If it’s repetitive, I automate it. If it’s noisy, I model it.
- 📈 Marketing & Product Analytics to boost user engagement and optimize spend
- 🤖 ML & Statistical Modeling that impacts GTM, retention, and ops
- 📊 Storytelling Dashboards using Power BI, Looker, Tableau
- 🔄 Automation using Python & APIs to save hours and scale smarter
- Boosted form completion rates by 25% via GenAI A/B test on UX improvements
- Reduced lead enrichment cost by 70% using a Python-based LLM scoring agent
- Built 3 Looker dashboards unifying AirTable & Sheets, improving ops efficiency by 30%
- Created a Slack-based AI chatbot cutting data lookup time from 1 hour → 5 minutes 🛠 Python • Looker • Slack API • Make.com • AirTable • Asana
- Contributed to a $13M client sale by modeling product lifespan with multivariate regression
- Built 5+ Power BI dashboards tracking KPIs across 400+ clients, enabling GTM performance insights
- Identified $0.5M in savings via performance benchmarking across multi-year data
- Created a Streamlit tool using decision trees to surface optimal operating ranges for customers
- Built alerting system to prevent $100K+ in annual losses using moving averages + technical rules
- Presented at Honeywell Global Tech Conference to 500+ engineers and execs 🛠 Python • Power BI • SQL • Streamlit • Regression • Forecasting
- Automated QA using Selenium & Python, reducing test cycles by 15%
- Managed 20+ production releases with Jenkins & RLM, improving uptime by 30% 🛠 Jenkins • Bash • RLM • Selenium • CI/CD
-
🎯 Credit Card A/B Testing
Modeled test outcomes across 1M+ users to identify offer variants with +0.25% lift in response rate. -
📊 MMM for Marketing ROI
Built log-log & square-root models in R across 3 years of weekly data to optimize media mix. -
🧮 Conjoint Pricing Strategy
Ran Monte Carlo WTP simulations on 1,200+ survey responses to identify price points with 2% market share. -
📱 Customer Segmentation
Clustered mobile buyers using k-means + mixture regression for personalized marketing based on price sensitivity.
🎓 MS in Business Analytics (GPA: 3.8/4.0)
Focus: Machine Learning, Causal Inference, Marketing Analytics
📍 San Francisco, CA
Also: MBA Quant Tutor for 50+ students — breaking down stats like t-tests & regression into business stories.
📫 Email: abarpan3@gmail.com
💼 LinkedIn: linkedin.com/in/arpan-banerjee98
💻 Projects: Check the pinned repos or reach out if you're curious about something!
“Automate the boring. Model the messy. Tell the story.”
— That's how I roll.