Caroline Hao
Senior Data Analyst
New York,N
Summary
Experienced Data Scientist with a strong foundation in data analysis and a history of providing valuable insights. Skilled in developing and executing data models to enhance decision-making within organizations. Proficient in SQL and Python, adept at working collaboratively with diverse teams to drive results.
Overview
7
7
years of professional experience
2031
2031
years of post-secondary education
Work History
Senior Data Analyst, Personalization
Saks.com (Saks Fifth Avenue)
New York, New York
10.2020 - Current
- Led technical and analytical initiatives across three luxury retail brands (Saks, Neiman Marcus, and Bergdorf Goodman), acting as a strategic liaison between data, marketing, engineering, and executive stakeholders.
- Spearheaded the development of a Unified Fraud Customer Identity System, consolidating cross-functional fraud and abuse signals into a centralized database to enhance detection accuracy and improve decision-making across marketing, service centers, and clienteling platforms.
- Built and deployed machine learning models for client segmentation and engagement prediction, enabling real-time personalization and optimized customer outreach.
- Designed experimentation strategies including A/B and multivariate tests to evaluate personalized marketing tactics and product features.
- Developed end-to-end data workflows for personalized communication systems, leveraging Python, SQL, Airflow, and Snowflake.
- Partnered with engineering and marketing stakeholders to deploy model-driven strategies in production, ensuring scalability and business alignment.
- Led QA processes, data monitoring, and documentation for client engagement and CRM systems.
- Created dashboards and automated performance tracking tools to measure model effectiveness and campaign impact.
Data Scientist
Criteo
New York, NY
04.2019 - 09.2020
- Built predictive benchmarks for advertiser launch and revenue forecasting using statistical models.
- Designed portfolio monitoring tools and risk-performance dashboards to evaluate client health.
- Worked with finance and strategy teams to optimize advertiser spend and mitigate high-risk exposure.
Data Scientist
C3 Alliance LLC
New York, NY
06.2018 - 04.2019
- Created ML models to analyze outdated NASA patents and identify commercial value and market risks.
- Delivered interactive visualizations and reports to executives and stakeholders.
Education
Ph.D. - Information Technology
Trine University
Detroit, MI01.2029
M.A. - Statistics
Columbia University
New York, NY 09.2016 - 12.2017
B.S. - Financial Mathematics
University of Liverpool
Liverpool, UK 09.2012 - 06.2016
Skills
- Python
- Pandas
- NumPy
- Scikit-learn
- PySpark
- SQL
- Spark
- dbt
- GitHub
- Snowflake
- AWS
- Airflow
- Supervised Learning
- Unsupervised Learning
- Anomaly Detection
- Hypothesis Testing
- A/B Testing
- Multivariate Testing
- Loss modeling
- Risk simulation
- Client segmentation
- Behavioral profiling
- Amperity
- SFCC
- Email Trigger Systems
- Seer Platform
- DAM
- QA Systems
- Legal Compliance
Data quality assurance
Advanced analytics
Core Skills
Python (Pandas, NumPy, Scikit-learn, PySpark), SQL (Advanced), Spark, dbt, GitHub, Snowflake, AWS (S3, EC2), Airflow (DAGs), Supervised/Unsupervised Learning, Anomaly Detection, Hypothesis Testing, A/B & Multivariate Testing, Loss modeling, Risk simulation, Client segmentation, Behavioral profiling, Amperity, SFCC, Email Trigger Systems, Seer Platform, DAM, QA Systems, Monitoring, Legal Compliance
Selected Projects
- Unified Fraud Customer Identity System, Built a centralized fraud and abuse flagging system across Saks, SFA, and NMG., Consolidated customer data using Amperity, SFMC, and POS for better visibility and actionability., Resulted in improved fraud detection accuracy and streamlined cross-team decision-making.
- Dynamic Client Book (DCB), Designed a smart clienteling tool integrating behavioral data, sales history, and LTV scores., Automated client ranking using Python, SQL, and Airflow; enabled stylists to prioritize top clients., Increased client engagement and conversion rates across 500+ associates with data-driven personalization.
- Promo Baseline Model, Created a machine learning model to simulate non-promo daily baseline sales using sales trends, inventory, MMM inputs, and engagement signals., Enabled comparison against actual campaign results to measure incremental lift and ROI., Used by cross-functional teams (Marketing, Finance, Merchandising) to guide strategy and investment decisions.
Timeline
Senior Data Analyst, Personalization
Saks.com (Saks Fifth Avenue)
10.2020 - Current
Data Scientist
Criteo
04.2019 - 09.2020
Data Scientist
C3 Alliance LLC
06.2018 - 04.2019
M.A. - Statistics
Columbia University
09.2016 - 12.2017
B.S. - Financial Mathematics
University of Liverpool
09.2012 - 06.2016
Ph.D. - Information Technology
Trine University
Similar Profiles
Teresa DattiloTeresa Dattilo
Jewelry Coordinator at Saks.comJewelry Coordinator at Saks.com
Ana MatosAna Matos
General Laborer at Saks.comGeneral Laborer at Saks.com
Nick SmytheNick Smythe
Senior Producer at Saks.ComSenior Producer at Saks.Com
Maveline Mipo ThelusmeMaveline Mipo Thelusme
Assistant Project Manager – Media & Influence at LVMH Fragrance BrandsAssistant Project Manager – Media & Influence at LVMH Fragrance Brands
Avery SteeleAvery Steele
Senior Associate, Client Solutions at Gerson Lehrman GroupSenior Associate, Client Solutions at Gerson Lehrman Group