About
Highly accomplished Data Science and Business Analytics professional with over 14 years of experience at leading firms like Meta and Accenture. Expertly translates complex business problems into high-impact Machine Learning and Data Mining solutions, delivering actionable insights and driving strategic decision-making across diverse international markets.
Work
Chicago, IL, US
→
Summary
Leads cross-functional initiatives at Meta, designing and implementing advanced data pipelines and machine learning models to optimize marketing experiments and campaign performance for US and international markets.
Highlights
Spearheaded the design and execution of marketing experiments and Ad campaigns for Meta, collaborating closely with cross-functional marketing teams to drive strategic decision-making.
Developed and deployed robust Machine Learning models for propensity targeting across US and international markets, enhancing campaign effectiveness.
Engineered resilient Data Engineering pipelines to support on-platform and off-platform campaign measurement, utilizing randomized control trials (RCT) with synthetic lookalike methodologies.
Charlotte, NC, US
→
Summary
Leveraged advanced analytical techniques including Market Basket Analysis, Time Series Forecasting, and Anomaly Detection to provide actionable insights for diverse business units.
Highlights
Developed a robust Spark, Python, and R script for quarterly Market Basket Analysis, processing point-of-sale transactions from the data warehouse and loading results into Data Mart for ≈2.2K business units.
Designed and deployed an interactive Shiny dashboard for Time Series Forecasting (ARIMAX/Prophet), visualizing trends, seasonality, and providing 365-day sales forecasts.
Created a Python script for Anomaly Detection, automatically flagging anomalous transactions and updating the data mart, improving data quality and integrity.
Executed Cluster and Discriminant Analysis (Python/R) using Hierarchical and K-Means clustering, identifying relevant clusters for business profile segmentation and delivering key insights to stakeholders.
Charlotte, NC, US
→
Summary
Supported over 50 graduate students in Visual Analytics, providing guidance on Tableau, D3.js, and R Shiny dashboards.
Highlights
Provided primary technical and conceptual support to over 50 graduate students in the Visual Analytics course, focusing on Tableau, D3.js, and R Shiny dashboard development.
Amsterdam, North Holland, Netherlands
→
Summary
Analyzed financial instruments and led ETL development for a major insurance and asset management client, optimizing data warehousing and reporting processes across Netherlands and India.
Highlights
Conducted quantitative analysis and statistical modeling using R to assess performance of funds and diverse financial instruments for a leading insurance and asset management client organizations in the Netherlands.
Collaborated with data architects and business stakeholders to design and develop OLAP Cubes using SSAS tabular model, facilitating factsheets and sales reports, and implementing SSRS reports with Data Analytic Expressions.
Served as a Senior ETL Developer, utilizing Informatica PowerCenter to design, develop, and maintain ETL workflows for data warehouses, data marts, and Hadoop ecosystems.
Automated daily business reports using UNIX shell scripting, SQL, and PL/SQL, reducing manual effort by 3 FTE and significantly improving performance of databases and ETL tasks.
Skills
Languages
Python, SQL, R, Linux Shell Scripting, Java.
Machine Learning
Classification, Regression, Clustering, Association Rule Mining, Anomaly Detection Algorithms, Dimensionality Reduction, Time Series Analysis, Ensemble Models, Hyperparameter Tuning, Regularization, Topic Modelling (LDA), Word2Vec, Sentiment Analysis.
Statistical Modeling
Hypothesis Testing (t-test, chi square test etc.), ANOVA, Design of Experiments.
Platforms/Libraries/Tools
scikit-learn, H2O, R (Caret), Informatica PowerCenter.
Data Visualization
Tableau, R(Shiny), Matplotlib, Seaborn.
Databases and Big Data
Presto, Spark (PySpark), Hive, Oracle, Microsoft SQL Server, MySQL, Teradata, Hadoop.