Machine learning & predictive analytics
Random Forest, Logistic Regression, and K-Means models with feature engineering on AWS SageMaker-compatible stacks and Azure Databricks.
Data Analyst · 3+ Years Experience · Syracuse, NY
Turning complex data into actionable business insights.
Data Analyst with 3+ years of experience delivering end-to-end analytics across retail and IT consulting. Proficient in Python, SQL, and R with expertise in machine learning, ETL pipelines, and cloud platforms (AWS, Azure Databricks).
Syracuse, NY
$4.2M
Annualized Cost Avoidance
31%
Forecast Accuracy Improved
19%
Repeat Purchase Lift
91%
Churn Model Accuracy
25+Power BI Reports Built
About
Analytics built for scale and stakeholder trust
Results-driven Data Analyst with 3+ years of experience delivering end-to-end analytics solutions across retail and IT consulting environments in the US and global markets. Proficient in Python, SQL, and R with hands-on expertise in machine learning (Random Forest, Logistic Regression, K-Means Clustering), ETL pipeline development (AWS Glue, SSIS, Informatica), and cloud platforms (AWS, Azure Databricks). I translate complex datasets into actionable insights through Tableau, Power BI, and Looker dashboards-driving cost avoidance, churn reduction, and revenue growth.
I partner with product, finance, and marketing stakeholders in Agile and Waterfall environments to enforce data governance, standardize KPIs, and accelerate data-driven decisions. From demand forecasting at Kroger to enterprise reporting at Hexaware, I focus on pipelines, models, and dashboards that deliver measurable business outcomes.
Experienced collaborating with cross-functional teams to enforce data governance standards and deliver decision-ready insights at scale.
What I bring
ETL & cloud data pipelines
AWS Glue, Lambda, SSIS, Informatica, and ADF pipelines ingesting high-volume transactional data with sub-2-hour freshness SLAs.
Dashboard & KPI reporting
Tableau, Power BI, and Looker dashboards with DAX, executive KPIs, and self-serve reporting for cross-functional teams.
Data governance & stakeholder delivery
KPI standardization, requirement gathering, and Agile delivery in Jira and Confluence across product, finance, and marketing.
Current focus
Python · SQL · Tableau · Power BI · Looker · AWS · Azure Databricks · ML · ETL · Data Governance
Education
Masters in Information Systems
Syracuse University
Syracuse, NY, USA
Bachelor of Technology in Computer Engineering
D. Y. Patil Deemed to be University, Ramrao Adik Institute of Technology
Navi Mumbai, India
Process
Data workflow
How I move from requirements to validated pipelines, models, dashboards, and business outcomes.
Requirements
Stakeholder interviews, KPI definitions, and data governance alignment.
Data Wrangling
Cleaning, validation, EDA, and exploratory analysis with Python and SQL.
Modeling & KPIs
ML models, statistical testing, and standardized metrics across teams.
Dashboard Design
Tableau, Power BI, and Looker views with DAX and self-serve reporting.
ETL & Automation
AWS Glue, SSIS, Informatica, and ADF pipelines with refresh monitoring.
Insight Delivery
Executive summaries, A/B test readouts, and data storytelling.
Requirements
Stakeholder interviews, KPI definitions, and data governance alignment.
Data Wrangling
Cleaning, validation, EDA, and exploratory analysis with Python and SQL.
Modeling & KPIs
ML models, statistical testing, and standardized metrics across teams.
Dashboard Design
Tableau, Power BI, and Looker views with DAX and self-serve reporting.
ETL & Automation
AWS Glue, SSIS, Informatica, and ADF pipelines with refresh monitoring.
Insight Delivery
Executive summaries, A/B test readouts, and data storytelling.
Skills
Skills built for analytics delivery
Tools and technologies I use for data wrangling, modeling, visualization, ETL, and cloud analytics.
Programming & Query
Languages and query tools for analytics, modeling, and warehouse-scale reporting.
- Python
- R
- SAS
- SQL
- Snowflake
- SQL Server
- MySQL
- PL/SQL
- MATLAB
Data Analysis & Visualization
Cleaning, EDA, validation, governance, and executive-ready dashboards.
- Data Cleaning
- Data Wrangling
- EDA
- Data Validation
- Data Governance
- Tableau
- Power BI
- Looker
- Alteryx
- Advanced Excel
- DAX
- KPI Reporting
- Data Storytelling
Machine Learning
Predictive modeling, clustering, feature engineering, and model evaluation.
- Random Forest
- Logistic Regression
- K-Means Clustering
- PCA
- Linear Regression
- Decision Trees
- Feature Engineering
- Scikit-learn
- TensorFlow
- A/B Testing
- Predictive Analytics
ETL & Cloud
Pipeline development and cloud analytics across AWS, Azure, and GCP.
- AWS Glue
- AWS Lambda
- AWS Redshift
- AWS Athena
- SSIS
- Informatica
- Azure Data Factory
- Azure Databricks
- PySpark
- Snowflake
- Delta Lake
Databases
Relational and NoSQL platforms for analytics and application data.
- MySQL
- PostgreSQL
- SQL Server
- Oracle
- MongoDB
Tools & Collaboration
Version control, project delivery, and professional analytics tooling.
- Git
- GitHub
- GitLab
- Jira
- Confluence
- Agile
- Scrum
- Waterfall
- Jupyter Notebook
- VS Code
Impact
Selected impact
Measurable outcomes from Kroger and Hexaware Technologies-grounded in my professional experience.
$4.2M
Inventory overstock prevented
Kroger demand forecasting
31%
Demand forecast accuracy gain
Kroger ML pipelines
19%
Repeat purchase rate lift
Kroger segmentation
37%
Fewer pipeline failures
Kroger AWS Glue ETL
16%
Campaign ROI increase
Kroger A/B testing
41%
Fewer reporting discrepancies
Kroger data governance
91%
Churn classification accuracy
Hexaware ML models
52%
Query performance boost
Hexaware Databricks migration
Experience
Professional experience
End-to-end analytics across retail operations and global IT consulting engagements.
Data Analyst
KrogerUSA
Sep 2025 - Present
- Developed end-to-end ML pipelines using Python (Scikit-learn, Pandas) and Random Forest models with feature engineering on AWS SageMaker-compatible architecture via AWS S3 and Redshift, improving demand forecast accuracy by 31% and preventing $4.2M in annualized inventory overstock across the Southeast region.
- Architected customer segmentation models using K-Means Clustering and PCA on AWS Redshift, enabling hyper-targeted promotions across 4.2M+ loyalty members and delivering a 19% lift in repeat purchase rate within 60 days of rollout.
- Designed and published Tableau dashboards and Looker self-serve reports tracking 18+ KPIs across 2,800+ store locations, compressing weekly executive reporting cycles from 3 days to same-day delivery.
- Engineered automated ETL pipelines via AWS Glue and Lambda to ingest and transform 60GB+ of daily transactional data from 14 upstream systems, reducing pipeline failures by 37% and maintaining a consistent sub-2-hour data freshness SLA.
- Developed a Python-based A/B testing framework integrated with AWS Athena, delivering statistically validated promotional insights that increased campaign ROI by 16% over two quarters.
- Led data governance and KPI standardization across Agile sprint cycles in Jira and Confluence, cutting reporting discrepancies by 41% across product, finance, and merchandising stakeholders.
PythonAWSRedshiftTableauLookerScikit-learnAWS GlueK-MeansPCA
Data Analyst
Hexaware TechnologiesIndia
Jan 2022 - Jul 2024
- Developed 25+ Power BI reports with DAX measures and Alteryx-driven data prep across 6 client engagements, cutting manual reporting effort by 34 hours/month with 60% faster turnaround.
- Built enterprise ETL pipelines using SSIS and Informatica to consolidate data from Oracle, SQL Server, and MySQL into Azure Data Lake Storage and SSAS cubes, reducing processing latency by 44% across 300+ daily report consumers.
- Migrated legacy on-premise infrastructure to Azure Databricks and processed large-scale datasets using PySpark, boosting query performance by 52% and enabling self-serve analytics for 5 business teams.
- Trained and validated Logistic Regression and Random Forest models in Python to predict client churn and risk tiers, achieving 91% classification accuracy and enabling proactive retention outreach to 1,400+ at-risk accounts.
- Conducted EDA and root cause analysis on behavioral datasets using Pandas, Seaborn, and Matplotlib, driving a churn reduction program with 14% improvement in two quarters.
- Coordinated 3 concurrent client workstreams under Waterfall and SDLC frameworks, sustaining 100% on-time milestone delivery over 2.5 years.
Power BIDAXAlteryxSSISInformaticaAzure DatabricksPySparkPython
Projects
Analytics deliverables & case studies
Representative work themes from Kroger and Hexaware-highlighting pipelines, models, and reporting outcomes.
Featured project
Machine LearningData Analytics
Retail Demand Forecast ML Pipeline
Problem
Southeast region inventory planning needed more accurate demand forecasts to reduce overstock and improve replenishment decisions.
Built
End-to-end ML pipelines in Python (Scikit-learn, Pandas) with Random Forest models and feature engineering on AWS S3 and Redshift, SageMaker-compatible architecture.
Impact
Improved demand forecast accuracy by 31% and prevented $4.2M in annualized inventory overstock.
PythonScikit-learnPandasAWS S3AWS RedshiftRandom Forest
View case study →
Machine LearningData Analytics
Customer Segmentation & Loyalty Analytics
Problem
Marketing needed hyper-targeted promotions across a large loyalty member base with clearer segment definitions.
Built
K-Means Clustering and PCA models on AWS Redshift to segment 4.2M+ loyalty members for promotional targeting.
Impact
Delivered a 19% lift in repeat purchase rate within 60 days of rollout.
PythonK-Means ClusteringPCAAWS RedshiftSQL
View case study →
BI Dashboard
Supply Chain & Merchandising KPI Dashboards
Problem
Executives needed faster visibility into supply chain and merchandising performance across thousands of store locations.
Built
Tableau dashboards and Looker self-serve reports tracking 18+ KPIs across 2,800+ store locations.
Impact
Compressed weekly executive reporting cycles from 3 days to same-day delivery.
TableauLookerKPI ReportingDashboard DevelopmentSQL
View case study →
ETL & CloudData Analytics
AWS Glue ETL & Data Freshness Automation
Problem
Daily transactional data from 14 upstream systems required reliable ingestion with minimal pipeline failures and low latency.
Built
Automated ETL pipelines via AWS Glue and Lambda ingesting and transforming 60GB+ of daily data.
Impact
Reduced pipeline failures by 37% and maintained a consistent sub-2-hour data freshness SLA.
AWS GlueAWS LambdaPythonETLAWS S3AWS Athena
View case study →
BI Dashboard
Enterprise Power BI Reporting Suite
Problem
Six client engagements relied on fragmented Excel workflows with slow manual reporting cycles.
Built
25+ Power BI reports with DAX measures and Alteryx-driven data preparation across client datasets.
Impact
Cut manual reporting effort by 34 hours/month with 60% faster turnaround.
Power BIDAXAlteryxAdvanced ExcelSQL
View case study →
Machine LearningData Analytics
Client Churn Prediction & Retention Analytics
Problem
Client accounts needed proactive churn risk identification ahead of renewal windows.
Built
Logistic Regression and Random Forest models in Python with EDA using Pandas, Seaborn, and Matplotlib.
Impact
Achieved 91% classification accuracy and drove a 14% churn reduction improvement in two quarters.
PythonLogistic RegressionRandom ForestPandasSeabornScikit-learn
View case study →
Contact
Let's connect on your next Data Analyst hire
Open to Data Analyst, Analytics Engineer, and BI roles. Let's discuss how I can help your team with Python, SQL, cloud pipelines, and executive reporting.
Based in Syracuse, NY · Open to remote and relocation · 3+ years analytics experience
Syracuse, NY
+1 (315) 395-1339