I am a business professional with experience in Business Development, Sales, CRM, Manufacturing and Entrepreneurship, now specializing in Data Analytics, Business Intelligence and data-driven decision-making.

I combine business understanding with data and technology to transform business problems into measurable insights, actionable recommendations and business decisions.

Business Problem → Data → Analysis → Insight → Action

📍 Bangalore, India
💼 Assistant Manager – Business Development
🎓 Pursuing MS in Data Science through the Scaler–Woolf pathway
🎯 Target roles: Data Analyst | Business Analyst | BI Analyst

• 💼 LinkedIn: Vijay Kumar
• 💻 GitHub: @vijaybsbs

BigQuery / GoogleSQL / Looker Studio

End-to-end e-commerce analytics covering data quality, customer behaviour, geography, order economics, payments, logistics, delivery performance, customer experience and RFM analysis.

Selected findings & business implications

• 97% of active customers are one-time buyers; repeat customers represent only 3% → retention initiatives should focus on converting one-time buyers into repeat customers.
• 48.85% of customers account for 80% of observed customer value → customer-value concentration can help prioritize retention and targeted engagement.
• São Paulo, Rio de Janeiro and Minas Gerais represent 61.24% of recent high-value one-time customers → these markets provide a clear geographic focus for retention and cross-sell initiatives.
• 80.82% of recent high-value one-time orders contain a single item → cross-sell and basket-expansion opportunities should be investigated for high-value one-time customers.

Key skills: SQL • BigQuery • Data Modelling • CTEs • Window Functions • RFM • KPI Analysis • Dashboarding

🔗 View Project

BigQuery / GoogleSQL / Looker Studio

Retail sales and inventory analysis across 50 stores and 35 products, covering revenue, cost, product performance, store performance, pricing, inventory risk and Pareto analysis.

Selected findings & business implications

• $14.44M revenue, $4.01M gross profit and 27.79% gross margin.
• The top 15 of 35 products (43%) generate approximately 80.08% of revenue → revenue is concentrated, but not at a classic 80/20 level; availability and replenishment of these high-contribution products deserve priority.
• Toys is the largest revenue category at 35.26%, while Electronics has the highest gross margin at 44.57% → category strategy should balance revenue scale with margin contribution.
• 157 store-product combinations have no inventory record, while 7 duplicate inventory rows require data-quality attention → inventory decisions should account for incomplete and duplicated inventory records.
• 3 inventory records have stock despite no historical sales → these combinations warrant review for assortment fit, local demand or potential overstock.

Key skills: SQL • Window Functions • Ranking • Pareto Analysis • Retail Analytics • Inventory Analysis • Dashboarding

🔗 View Project

Python / EDA / Statistics

Bike rental demand analysis using exploratory data analysis and statistical hypothesis testing to evaluate the impact of working days, seasons, weather and environmental factors on demand.

Statistical findings

• Working days: independent 2-sample t-test → t = 1.210, p = 0.2264 → no statistically significant difference in average rentals between working and non-working days.
• Season: one-way ANOVA → F = 236.95, p = 6.16 × 10⁻¹⁴⁹ → rental demand differs significantly across seasons; Fall has the highest median and Spring the lowest in the analysis.
• Weather: one-way ANOVA → F = 65.53, p = 5.48 × 10⁻⁴² → rental demand differs significantly across weather conditions; clear weather has the highest median, while light snow has the lowest.
• Season × Weather: chi-square test → χ² = 46.10, df = 6, p = 2.83 × 10⁻⁸ after excluding the single heavy-rain observation because the original expected-frequency assumption was violated → season and weather are statistically associated.

Business implication: demand planning should account for season and weather conditions rather than treating working-day status alone as a significant demand driver.

Key skills: Python • Pandas • EDA • Statistics • Hypothesis Testing • Business Analytics

🔗 View Project

Tableau

Interactive business intelligence dashboard focused on sales performance, revenue targets, regional performance, freight costs, product-segment trends and customer retention.

Selected findings & business implications

• Revenue reached 9.24M against a 9.751M target, representing approximately 94.8% target achievement → the business was below its revenue target by about 0.51M in the dashboard period.
• Order quantity was 129,284 against a target of 372,420, representing approximately 34.7% target achievement → quantity performance shows a substantial gap relative to the target.
• The dashboard reports an average discount of 4.96%, freight expense of 119,699 and an average unit price of 88, providing a basis for monitoring pricing, discounting and logistics costs together.
• Regional revenue varies materially across the states shown in the dashboard, including South Australia (962,572), Tasmania (795,403) and Northern Territory (514,268) → regional performance can be compared to identify differences in revenue contribution.
• Revenue trends vary across wine segments over time: Red Wine shows a relatively consistent pattern, while Rose/Sparkling Wine shows greater volatility and White Wine records a pronounced revenue spike around 2012.
• Order quantity increases across the displayed years, rising from approximately 25K in 2010 to 42K in 2013 → the dashboard indicates increasing order volume over the period.
• The customer retention view shows a growing contribution from customers associated with earlier ordering periods over time, providing a basis for monitoring repeat-order behaviour and customer retention.

Business focus: revenue performance • target tracking • regional analysis • wine-segment trends • freight analysis • customer retention

🔗 View Tableau Project

SQL + Python

End-to-end restaurant analysis covering pricing, ratings, online delivery, customer engagement, cuisine analysis, segmentation, city-level market profiling and a project-defined Market Opportunity Score.

Selected findings & business implications

• 90.59% of the 9,551 restaurant records are from India → overall dataset-level conclusions are strongly influenced by the Indian market.
• Customer engagement is highly skewed: 31 median votes vs 157 mean votes, with a maximum of 10,934 votes.
• 1,094 restaurants have zero votes, while 2,148 restaurants have Rating ≤ 1.0 and Votes ≤ 3 → engagement level should be considered when interpreting restaurant performance.
• Higher price ranges show higher average ratings and recorded engagement: Price Range 1 = 2.33 rating / 36 votes versus Price Range 4 = 3.66 rating / 404 votes.
• 3,022 Indian restaurants serving Indian cuisine do not offer online delivery → the dataset shows a measurable digital-adoption gap.
• The highest-voted city–cuisine combination is New Delhi — North Indian | Mughlai with 27,951 total votes.

Business focus: restaurant performance • customer engagement • pricing • digital adoption • cuisine analysis • city markets

Key skills: SQL • Python • Pandas • EDA • Segmentation • Business Analysis

🔗 View Project

Python / Pandas

Logistics data analysis and feature engineering to transform trip-level operational data into model-ready features for route, delivery and performance analysis.

Selected findings & business implications

• 144,867 operational records represent 14,817 unique trips across approximately 27 days of data.
• Average actual trip time is 417 minutes vs 214 minutes estimated by OSRM → actual operations take substantially longer than routing estimates on average, making estimate-vs-actual gaps important for operational planning.
• Average actual distance is 234 km vs 285 km OSRM estimated distance → routing distance and observed operational distance differ materially and should be evaluated separately rather than treated as interchangeable measures.
• The dataset contains 1,500+ source/destination logistics centers, providing a broad geographic basis for route and hub-level analysis.
• 293 source-name and 261 destination-name values were missing before preprocessing, representing less than 0.3% of the 144,867 records; no duplicate records were identified.

Business focus: trip-level grain • route performance • actual vs estimated distance/time • operational feature engineering

Key skills: Python • Pandas • Data Cleaning • Feature Engineering • Operational Analytics

🔗 View Project

Sales • Revenue Analysis • CRM Analytics • Customer Analytics • Lead Funnel Analysis • Market Analysis • KPI Reporting

SQL • GoogleSQL • BigQuery • Python • Pandas • Excel • Exploratory Data Analysis • Statistics

Tableau • Looker Studio • Dashboarding • KPI Analysis • Data Visualization

Generative AI • Prompt Engineering • AI-assisted Analytics

Git • GitHub • Google Colab • Jupyter • Google Sheets

My career sits at the intersection of business, sales, data and technology.

I bring practical experience across Business Development, Sales, CRM, Revenue Analysis, Manufacturing and Entrepreneurship, with a growing focus on data-driven decision-making.

• Sales and revenue performance analysis; CRM activity and lead-funnel analytics
• Daily sales productivity, KPI tracking and performance dashboards
• Created a lead generation → nurture → conversion SOP supported by daily sales reporting

• Architect, builder and dealer/channel engagement; project and specification business
• Cross-functional coordination with marketing and sales teams
• Conducted knowledge-sharing / L&L sessions for design and execution teams

I use SQL, Python, Excel, BigQuery and BI tools to connect business questions with data and translate analysis into actionable business insights.

Business Problem → Data → Analysis → Insight → Action

I am pursuing a Master of Science (MS) in Data Science through the Scaler learning pathway, with the academic degree awarded by Woolf Higher Education Institution.

Core Areas:
Data Analytics • Statistics • SQL • Python • Machine Learning • Data Visualisation • Business Intelligence • Applied Data Science

Saïd Business School, University of Oxford

Completed the Introduction to Advanced Business Analytics with AI course, focused on applying business analytics and AI to data-driven decision-making, strategic and operational outcomes, and responsible AI adoption.

Key Areas:
Business Analytics • Generative AI • AI for Decision-Making • Predictive & Prescriptive Analytics • AI Risk & Ethics • Real-World Case Studies

• Completed: August 2026
• Academic Credit: 1 credit
• Credential: University of Oxford, Saïd Business School

Business Management • Strategy • Marketing • Operations • Entrepreneurship

• Advanced SQL and analytical problem solving
• Python for data science and applied analytics
• Statistics and applied data analysis
• Generative AI and LLM applications
• AI-assisted business analytics

I am interested in opportunities where I can combine business understanding, analytics and technology to solve real-world business problems.

Primary: Data Analyst • Business Analyst • BI Analyst

Growth Areas: Business Analytics • Applied Analytics • Data Science • AI & Analytics