Shantan Tanuku

1. Tableau Development & Business Intelligence

• Led development of 20+ interactive Tableau dashboards across Sales, Marketing, Finance, and Supply Chain using LOD expressions, parameter filters, and KPI alerts to support executive decision-making.
• Integrated data from MySQL, ERP (Sage), Google Analytics 4 (GA4), and CRM systems to centralize reporting across pricing, marketing funnels, campaign performance, and inventory control.
• Built GA4-powered dashboards to monitor campaign performance (CAC, ROAS, bounce rate, conversion), enabling real-time visibility and faster adjustments by Marketing team.
• Designed forecasting dashboards using historical sales, seasonal patterns, and inventory triggers to guide Sales and Ops planning, reducing stockouts and overstock risk.
• Enabled Sales team to benchmark product pricing against competitors daily via Tableau dashboards, reducing price adjustment lag from days to hours.
• Reduced dashboard refresh time from 8+ seconds to under 2 seconds by optimizing SQL views and Tableau extracts.
• Implemented Tableau governance: Row-Level Security (RLS), version control, naming conventions, and performance standards.
• Delivered high-impact PowerPoint presentations for leadership, translating Tableau insights into pricing narratives, performance overviews, and actionable recommendations.
• Trained 30+ users in Tableau usage and data literacy, achieving 70% self-service BI adoption and significantly reducing manual reporting.
• Supported ad hoc analysis and pricing models using Excel, including pivot tables, macros, and what-if scenarios for finance and marketing planning sessions.

2. Pricing Intelligence & Competitor Scraping

• Built Python-based pricing engine on AWS to scrape competitor pricing daily from over 10 major UK retailers and marketplaces, feeding directly into internal BI systems.
• Integrated competitor prices with ERP cost data to simulate real-time product-level margin scenarios, enabling monthly pricing updates across 1,000+ SKUs.
• Developed predictive pricing models in Python and SQL to forecast margins and compare forecasted vs actual profitability, flagging margin risk across product segments.
• Delivered automated Tableau dashboards that visualized pricing performance, margin thresholds, and competitor comparisons, enabling Sales team to act on daily price intelligence.
• Produced monthly pricing reports and PowerPoint decks that guided campaign pricing, markdown planning, and retail positioning, leading to 6.4% margin improvement across key categories.
• Worked closely with ERP developers to automate pricing logic and triggers using AWS pipeline as data source.
• Handled and normalized supplier price files across 20+ vendors and used benchmark data to support commercial negotiations and reduce procurement costs.
• Created pricing summary models and interactive dashboards in Excel for category managers, including competitive spread analysis and supplier margin waterfall charts.

3. ETL, Automation & Cloud Infrastructure

• Designed and deployed ETL pipelines using Python, Airflow, and Power Automate to ingest, clean, and transform data from GA4, SharePoint, ERP, and CRM platforms.
• Deployed automated scraping and pricing workflows on AWS EC2 and Lambda, storing daily snapshots for historical price tracking and analysis.
• Synced cleaned datasets into internal SQL-based data warehouse, powering near real-time updates for Tableau dashboards used by Sales, Pricing, and Marketing.
• Automated monthly reports and dashboards using Python scripts and Tableau APIs, eliminating 40+ hours per month of manual reporting effort.
• Enforced data normalization and schema governance across all pipelines, ensuring consistent, reliable output for both Tableau and Excel-based analysis tools.
• Used Excel for daily reconciliation reports, supplier import validation, and manual data checks where source data was partially structured or inconsistent.

• Designed AI models using NLP in Python for sentiment analysis, classifying customer feedback across multiple channels; enabled proactive engagement, reduced churn, and improved overall user experience.
• Built multi-class classification models to categorize customer interactions, identify pain points, and tailor services—leading to higher customer satisfaction scores.
• Automated real-time data processing pipelines in Python, enabling faster insight generation and more agile decision-making aligned with shifting customer trends.
• Integrated IBM Watson Speech-to-Text to transcribe call centre audio, enabling scalable text-based analysis; reduced manual effort and improved service quality and turnaround time.
• Performed Exploratory Data Analysis (EDA) in Python to uncover patterns in customer behaviour; used heatmaps, correlation plots, and trend analysis to guide engagement strategy.
• Refined and retrained 12 AI models for customer profiling, increasing accuracy and responsiveness through continuous validation and feedback loops, supporting personalized service delivery.

• Dashboard Development & Data Visualization
  Designed strategic Tableau dashboards for Sales, Finance, and IT teams, driving data-informed decision-making. Applied Tableau best practices to improve user comprehension and adoption by 30%.
• SQL & Data Extraction
  Developed optimized SQL views to streamline data access, improving report accuracy and reducing retrieval time by 40%. Partnered with data engineering teams to ensure data integrity and seamless integration.
• User Training & Enablement
  Conducted Tableau training sessions for 50+ business users, increasing overall self-service analytics adoption by 25%. Created tailored training content to elevate organizational data literacy.
• Tableau Server Administration
  Maintained 99.9% Tableau Server uptime, ensuring secure and stable performance. Tuned server configurations to reduce dashboard load times by 20%, enhancing user experience across departments.
• Technical Documentation & Requirements Translation
  Authored technical documentation and translated business needs into clear, actionable specifications. Improved cross-functional collaboration and accelerated delivery timelines by 15%.

• Engineered classification system using Python and SQL to categorize transactions by advertiser brand, purchase channel, purchase type, location, and vertical—improving analytical accuracy and speeding up decision-making.
• Co-developed rule-based classification corpus in Python, defining robust patterns for reliable large-scale transaction tagging and categorization.
• Designed and executed advanced SQL queries with Regex to extract brand names from millions of records, significantly reducing manual effort and improving brand identification accuracy.
• Led development of automated merchant clustering pipeline in Python using pattern recognition to identify unknown merchants, enhancing completeness of transaction data.
• Built Python-based automation tools for 25-person Merchant Intelligence team, eliminating repetitive pattern detection tasks and saving substantial manual effort.
• Scaled brand analytics framework to handle millions of merchants, using SQL and Python automation to minimize human intervention while improving scalability and speed.
• Developed nationwide geographic data corpus in Python to enhance Master Location Capture (MLC) model; standardized and validated city/state/ZIP data for higher location accuracy.
• Created custom spell-checking and correction algorithm in Python to standardize city names using ZIP and state cross-referencing, improving location data reliability across millions of transaction records.

• Data Interpretation and Statistical Analysis: Analysed complex datasets using statistical techniques and programming languages like Python and R. Provided insights that informed business strategies and supported decision-making.
• Data Processing and Integrity Verification: Conducted extensive data processing, cleaning, and verification to ensure integrity and accuracy. Critical preparation steps enabled reliable, insightful analysis.
  Interactive Data Visualizations and Reporting: Created interactive visualizations and reports to communicate insights to non-technical stakeholders. Enhanced team’s ability to make data-driven decisions effectively.
• Feature Selection and Model Optimization: Identified relevant features for machine learning models, optimizing classifiers to enhance model performance. Strengthened machine learning expertise, resulting in more accurate predictive insights.