Data Scientist

*Senior Data Scientist | FinTech Innovators Inc., San Francisco, CA*

June 2022 – Present

- Developed a predictive credit scoring model using XGBoost that improved loan approval accuracy by 15%, resulting in a $3M annual reduction in default risk.

- Led a team of 4 data scientists to design real-time fraud detection algorithms harnessing Kafka and Spark Streaming, reducing false positives by 20%.

- Implemented an NLP-based chatbot for customer onboarding, increasing customer engagement metrics by 25%.

- Collaborated with engineers to deploy models on AWS SageMaker, ensuring scalability and low-latency performance.

Data Scientist | HealthTech Solutions, San Francisco, CA

August 2018 – May 2022

- Built and validated machine learning models to predict patient readmission rates, decreasing hospital readmission rates by 10%.

- Analyzed electronic health records (EHR) data to identify patterns, informing personalized treatment plans and operational improvements.

- Created interactive dashboards with Tableau for clinical staff, enabling real-time monitoring of key health metrics.

- Conducted A/B testing for digital health platform feature rollouts, leading to a 12% increase in user retention.

*Data Analyst | E-Commerce Co., Los Angeles, CA*

June 2016 – July 2018

- Designed customer segmentation models using clustering and decision trees, boosting targeted marketing ROI by 18%.

- Automated reporting pipelines with SQL and Python, reducing manual report generation time by 50%.

- Conducted market basket analysis, uncovering cross-sell opportunities that contributed to a 7% lift in average order value.

**Master of Science in Data Science**

University of California, Berkeley — Berkeley, CA

*2014 – 2016*

**Bachelor of Science in Computer Science**

University of California, Los Angeles — Los Angeles, CA

*2010 – 2014*

- AWS Certified Machine Learning – Specialty

- Certified Data Scientist (DASCA)

- TensorFlow Developer Certificate

- **Customer Churn Prediction Platform:** Developed end-to-end machine learning system to predict subscriber churn for a SaaS platform, achieving 85% accuracy and reducing churn by 10%.

- **Financial Portfolio Optimization:** Built a deep reinforcement learning model that dynamically adjusts investment portfolios based on market conditions, outperforming traditional strategies by 12%.

- **Health Data Privacy Framework:** Designed a federated learning framework to enable secure multi-institutional analysis of sensitive health data, enhancing collaborative research without compromising privacy.

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

- R (tidymodels, caret)

- SQL & NoSQL databases (PostgreSQL, MongoDB)

- Cloud Services (AWS, GCP, Azure)

- Big Data (Spark, Kafka, Hadoop)

- Visualization (Tableau, Power BI, Matplotlib, Seaborn)

- English (Fluent)

- Spanish (Conversational)