Jay Chauhan Email & Phone Number

Seattle, Wa, Us

• Leverage a comprehensive array of geospatial tools and develop scalable machine learning models to analyze customer behavior and mobility patterns, aimed towards strategic expansion of stores with potential to generate revenue exceeding $250M over next 5 years.• Manage the end-to-end development process of a suite of predictive models forecasting future store financials, including first year revenue, cost of operation, and market cannibalization, empowering finance stakeholders to quantitatively assess portfolio revenue and profit growth for financial reporting.• Drive cross-functional collaboration with finance and market planning stakeholders, leading diverse data science initiatives to address challenges such as geolocation analysis, competition assessment, market saturation, demand drivers, financial forecasting and feasibility and similar key factors instrumental in propelling market growth for Starbucks across North America.• Technologies Used: Python, PySpark, GeoPandas, Sedona, H3, Open Street Maps, Kepler, Databricks, Azure Cloud Services

Seattle, Wa, Us

• Developed and deployed a cloud-based forecasting pipeline in production, that consumes data of millions of transactions, and predicts store and daypart specific demand guidance for 16 core components, optimizing production to reduce waste and ensure maximum beverage availability across a network of 9500 Starbucks stores in North America on a weekly cadence.• Implemented a comprehensive labor forecast framework aimed at predicting daily store-level sales, facilitating strategic staffing decisions, and optimized workforce allocation leading to improved operational efficiency.• Consulted with store managers to iteratively gather feedback over usability and accuracy of data products deployed in stores.• Built Extract-Transform-Load(ETL) jobs to collect data from various data sources such as REST APIs, databases, SFTP feeds, and load into Azure Data Lake, which act as an aggregated data source for various machine learning pipelines and Tableau dashboards.• Technologies Used: Python, PySpark, Azure Cloud Services, Databricks, MySQL

Seattle, Wa, Us

Redwood City, California, Us

• Performed predictive analytics using Decision Trees to identify top predictors for user behaviour, engagement, conversion and churn.• Spearheaded a user segmentation project to cluster users based on in-app engagement using K-Means, predict clusters for new users and target clustered users with tailored upsells.• Analysed user data for growth experimentation, in order to achieve increased user engagement and monetization.• Technologies Used: R, Presto, SQL, Tableau

Seattle, Wa, Us

• Developed a data pipeline, transforming incoming data from a differential mobility analyser to quantify shifts in size and abundance of lipoproteins. • Created visualizations of the quantified size v/s abundance data and statistically compared the data using ANOVA in order to analyze the functions (or dysfunctions) of high density lipoproteins.• Technologies used: R, R Shiny

Paris, France, Fr

• Designed various table schemas as well as developed and implemented various T-SQL scripts including stored procedures, user defined functions, triggers etc. in MS SQL SERVER 2012• Developed ETL jobs to consolidate data from various sources such as MS SQL SERVER databases, MS excel files, CSV files, XML files etc. using an open source tool Talend• Migrated sites from SharePoint 2010 to SharePoint Online using Office 365 Developer Patterns and Practices Provisioning Schema, Microsft Azure and Sharepoint Apps

Master Of Science In Information Management, Data Science

Bachelor Of Engineering (B.E.), Information Technology