01A little about me
Curiosity meets
business impact.
I'm Sharad, a Data Scientist turning complex questions into decisions people can act on.
With 4+ years across retail and financial services, I bring together statistical thinking, machine learning, and a clear understanding of the business behind the data.
At Walmart, I build demand forecasts, pricing models, and customer segments with Python, SQL, PySpark, and Databricks. Previously at Accenture, I built fraud and risk models, transaction pipelines, and reporting for 100+ enterprise banking clients.
I own the question end to end: pulling the data, validating the model or experiment, and explaining the result to people who don't read code.
Let's talk dataFrom a good question
to a better decision.
Understand
Frame the problem and define what success means.
Build & validate
Engineer the data. Test the model. Challenge the assumptions.
Make it useful
Deploy, monitor, and communicate the result clearly.
State University of New York · 2025
Years in data science
Retail & financial services
Less forecast error
Demand forecasting at Walmart
Customers segmented
Behavioral cohorts for merchandising
02Experience
Real problems.
Measurable progress.
Building models, experiments, and analytics that make a difference in retail and financial services.
Walmart
CurrentData Scientist
Apr 2025 - Present
USA
Retail intelligence at scale
- Built weekly demand forecasts across ~40 store-item categories in PySpark on Databricks, comparing gradient boosting with seasonal ARIMA and choosing boosting for promotional spikes; forecast error fell ~18%.
- Segmented roughly 12M customers using K-Means, RFM, and basket-mix features, helping improve campaign response by about 15%.
- Modeled price elasticity across seasonal promotions using regression on ~3 years of transaction history, distinguishing markdowns that moved units from those that eroded margin; category margin improved ~6%.
More about this role
- Designed and analyzed A/B tests for search-ranking changes, using power calculations and guardrail metrics to support evidence-based decisions and improve add-to-cart rate by about 4%.
- Diagnosed repeat stockouts across regional distribution centers in SQL and Power BI, identifying replenishment lead-time as the dominant driver; store-level availability improved ~7%.
- Deployed forecasting and segmentation models on AWS SageMaker with MLflow tracking and drift alerts, replacing manual refreshes and reducing retraining cycle time to under 24 hours.
- Automated weekly merchandising summaries with SQL result sets and a retrieval-augmented LLM workflow, evaluated in MLflow for factual accuracy; saved analysts ~10 hours of write-up per week.
Accenture
Data Scientist
Jun 2020 - Jul 2023
India
Fraud detection & risk analytics
- Developed a transaction fraud classifier in Python and PySpark, comparing XGBoost with logistic regression and choosing XGBoost for rare-event recall; AUC rose from 0.82 to ~0.90.
- Engineered Apache Spark, Kafka, and SQL ingestion and ETL pipelines over ~2M daily transactions, restructuring joins for near real-time scoring and reducing decision latency by ~35%.
- Created behavioral, temporal, and merchant-level features in Pandas and Spark SQL, raising precision and recall on high-risk fraud segments by ~20%.
More about this role
- Validated rule and model changes with A/B tests and hypothesis testing, tuning alert thresholds to reduce false positives without suppressing genuine fraud; review volume dropped ~18%.
- Surfaced emerging fraud patterns with K-Means and Isolation Forest on unlabeled transaction streams, catching schemes the rules engine missed; undetected incidents fell ~27%.
- Published self-serve Power BI dashboards on fraud loss, alert volume, and risk scores for 100+ enterprise banking clients, replacing weekly manual decks.
- Partnered with risk and compliance leads on audit-defensible thresholds and wrote SQL views for monthly reviews; scoring covered ~14M flagged transactions yearly.
03The toolkit
A versatile stack.
A focused approach.
The tools and methods behind my work, from exploring a dataset to monitoring a production model.
Programming & Databases
Statistics & Experimentation
Analytics & BI
Machine Learning
Data Platforms & Cloud
Deployment & Applied GenAI
04Selected projects
The thinking.
The work. The impact.
Two projects that connect rigorous analysis with practical business decisions.
18 months of subscriber data
Logistic regression · Time splits
Discount vs. concierge outreach
Predictive modeling · Experimentation
Subscription Churn Prediction & Retention Test Design
Identifying who might leave is only half the question. This project pairs an interpretable churn model with a retention experiment to understand what makes subscribers stay.
Explore the approach
- Compared logistic regression with XGBoost, choosing logistic regression for the coefficient interpretability the retention team needed.
- Validated on a held-out quarter using stratified time splits after finding that seasonal renewals inflated random-split AUC by roughly 6 points.
- Ran a two-arm holdout test on the top churn decile. A chi-square readout showed concierge outreach retained ~11% more accounts than a discount offer.
Session-grain SQL fact table
~34% drop from cart to payment
Guest-checkout pilot
Customer analytics · Business intelligence
E-Commerce Funnel & Cohort Analytics Dashboard
Turning clickstream and order data into a shared view of the customer journey, then using cohort and funnel analysis to find where purchases fall through.
Explore the approach
- Modeled raw clickstream and order tables into a session-grain SQL fact table covering ~2M sessions, defining activation, repeat purchase, and 90-day retention as shared KPIs.
- Traced monthly signup cohorts through a five-step purchase funnel with SQL window functions, isolating a ~34% drop between cart and payment.
- Delivered a Tableau dashboard with a Power BI companion for finance. Recommended a guest-checkout pilot that recovered ~8% of abandoned carts.
05Let's connect
Good questions.
Great possibilities.
Have a data challenge, an interesting role, or an idea worth exploring? I'd love to hear about it.
sharad.b@ajobguide.comOpen to data science opportunities