I am a Data & Business Intelligence Analyst who enjoys turning raw, messy data into insights that business teams can actually use.
My experience spans dashboarding, analytics, and cloud data engineering – from cleaning and modelling data in SQL/Python to building modern data pipelines on AWS and visualising results in Power BI / Tableau / R Shiny.

I’m especially interested in:

• Building end-to-end analytics solutions – ingestion → modelling → dashboards
• Designing data lakes / ETL pipelines on cloud (AWS S3, Glue, Lambda, Athena)
• Creating interactive dashboards that answer real business questions and tell a clear story

I enjoy collaborating with stakeholders, asking “what decision will this chart actually drive?”, and then designing the data model and visuals around that.

AWS · S3 · Glue (PySpark) · Lambda · Athena · Parquet

• Built an end-to-end data lake on AWS for the YouTube Trending Kaggle dataset
• Landed raw CSV/JSON into an S3 landing zone and used Glue (PySpark) + Lambda to build a cleansed Parquet layer
• Registered datasets in the AWS Glue Data Catalog and queried them from Athena for analytics
• Documented the full architecture and data flow for interview-ready walkthroughs

🔗 Repo: YouTube-Trending-Video-Analysis

R · R Shiny · dplyr · ggplot2

• Designed an interactive sales performance dashboard for an e-commerce store
• Provided KPIs (revenue, units sold, AOV, transactions) with filters by product category and region
• Built visual breakdowns of sales by category/region and an interactive transaction table

(Screenshot in repo)
🔗 Repo: ONLINE_SALES_DASHBOARD

Python · SQL · Pandas · Scikit-learn · Tableau

• Cleaned audiobook metadata and listener behaviour data
• Performed exploratory data analysis to understand pricing, ratings and sales patterns
• Trained baseline ML models to explore what drives audiobook ratings
• Built Tableau visuals to communicate insights to non-technical stakeholders

🔗 Repo: AudioBook-Prediction-Using-ML-models

R · Time-Series · ARIMA

• Analysed 60+ years of defence budget data
• Performed stationarity tests (ADF, PP, KPSS) and time-series diagnostics
• Built ARIMA models and produced forward forecasts with interpretation

🔗 Repo: us-military-spending-forecasting

Power BI · DAX · Power Query · Drill-through · Bookmarks

• Built a 4-page HR analytics dashboard to monitor attrition KPIs and uncover key drivers across department, job role, overtime, satisfaction, travel, age band, and education
• Implemented a Decomposition Tree for interactive root-cause exploration and a heatmap matrix (Role × Satisfaction) to surface high-risk combinations
• Added an Employee Detail drill-through page with searchable Employee ID slicer and reset bookmarks for clean default states and smooth navigation
• Designed clear tooltips (rate + base) and consistent slicers to improve interpretability and reduce “small sample size” misreads

🔗 Repo: powerbi-hr-attrition-dashboard

• GitHub: @Vikas-2703
• LinkedIn: https://www.linkedin.com/in/vikas-66161921b/)

Always happy to talk about data, analytics, dashboards, and cloud projects!