Hi, I'm Abhishek Dwivedi — a Data Analyst with 8+ years of experience transforming complex datasets into clear stories that drive business decisions.
A full-stack data toolkit — from ingestion to insight and beyond.
Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn for end-to-end analysis and model building.
Advanced SQL queries, CTEs, window functions across PostgreSQL, MySQL, BigQuery, and Snowflake.
Building interactive dashboards and reports that tell stories executives can act on instantly.
Predictive models, clustering, NLP, and time-series forecasting for real business problems.
Data pipelines and ETL workflows on AWS, GCP, and Azure at scale using Spark and Airflow.
Hypothesis testing, experiment design, Bayesian inference, and causal analysis.
A selection of end-to-end data projects spanning analytics, ML, and visualization.
Built an XGBoost classification model achieving 92% accuracy to predict customer churn for a telecom firm, saving an estimated $1.2M annually in retention spend.
Interactive Power BI dashboard with real-time KPIs, funnel analysis, and cohort retention charts deployed for a D2C brand with 200K+ monthly orders.
Time-series forecasting with Prophet + LSTM to reduce inventory holding costs by 22% for a mid-size FMCG manufacturer across 15 SKUs.
Multi-touch attribution model using Markov chains and Shapley values to redistribute $500K ad budget, improving blended ROAS by 34%.
A structured, end-to-end SQL project built on the AdventureWorks 2022 sample database using SQL Server Management Studio (SSMS). The project covers product catalogue analysis, inventory health monitoring, sales velocity, pricing & discount patterns, and advanced analytics using CTEs and window functions..
Gradient boosted regression model served via FastAPI, predicting property prices within 4.2% MAPE across 3 metro markets using 25+ features.
Tutorials, walkthroughs, and opinions on data, analytics, and the tools I use every day.