Data Scientist in Retail

Hard Skills

- Supervised & Unsupervised Machine Learning (Random Forest, XGBoost, K-Means, Neural Networks)

- Predictive Analytics & Demand Forecasting

- Customer Segmentation & Lifetime Value Modeling

- Big Data Technologies (Spark, Hadoop)

- SQL & NoSQL Databases (PostgreSQL, MongoDB)

- Python (Pandas, scikit-learn, TensorFlow, PyTorch)

- R & Shiny Dashboards

- Data Visualization (Tableau, Power BI, matplotlib, seaborn)

- A/B Testing & Experimentation

Soft Skills

- Strategic Problem Solving

- Cross-Functional Collaboration

- Effective Communication of Complex Data

- Agile & SCRUM Methodologies

- Critical Thinking & Innovation

- Customer-Centric Mindset

*Senior Data Scientist | RetailTech Solutions, New York, NY*

June 2022 – Present

- Led development of a predictive inventory optimization model using XGBoost, reducing stockouts by 18% and excess inventory by 22%.

- Designed customer segmentation models integrating transactional and demographic data, resulting in targeted marketing campaigns that increased conversion rates by 15%.

- Collaborated with marketing and store operations teams to automate weekly sales forecasting, decreasing manual effort by 40%.

- Implemented scalable data pipelines on Spark, improving data processing speed for real-time analytics.

Data Scientist | FreshFashion Retail, Chicago, IL

April 2019 – May 2022

- Developed machine learning models to predict customer churn and identify high-value customers, enhancing retention strategies with a 12% uplift in re-engagement.

- Conducted A/B testing for new loyalty program features, providing insights that increased enrollment by 25%.

- Created interactive dashboards with Tableau that visualized store performance metrics, empowering regional managers to make data-driven decisions.

- Integrated social media data streams into predictive models to analyze trending consumer preferences, decreasing product return rates by 9%.

*Data Analyst | RetailX, Los Angeles, CA*

January 2017 – March 2019

- Managed large-scale sales and customer data, performing exploratory data analysis to uncover purchasing patterns.

- Supported the deployment of a demand forecasting model that improved accuracy by 16% over existing methods.

- Developed quarterly reporting dashboards, streamlining executive reporting workflows and reducing manual report generation time by 30%.

**Bachelor of Science in Data Science & Analytics**

University of California, Los Angeles (UCLA), Graduated 2016

- Certified Analytics Professional (CAP) – 2023

- AWS Certified Data Analytics – Specialty – 2024

- TensorFlow Developer Certificate – 2022

Personalized Recommendation Engine for RetailStore

- Designed and implemented a hybrid collaborative and content-based filtering system in Python, boosting cross-sell sales by 20%.

Store Foot Traffic Prediction Model

- Developed a deep learning model using TensorFlow to predict daily store visitation, enabling staffing adjustments that improved customer service ratings by 8%.

Customer Lifetime Value (CLV) Prediction

- Built a robust CLV model utilizing RFM segmentation and regression techniques, enabling targeted retention offers, resulting in a 10% increase in customer lifetime revenue.

- Python (scikit-learn, TensorFlow, PyTorch, Pandas)

- R, Shiny, SQL

- Tableau, Power BI

- Spark, Hadoop Ecosystem

- AWS Cloud (S3, Lambda, SageMaker)

- Git, Docker, Jenkins

- English (Native)

- Spanish (Fluent)