Columbus, Ohio, United States
I measure what matters in influencer marketing — building causal inference frameworks (PSM, DiD, MMM) that connect multi-million-dollar investment in creator partnerships to real business outcomes. My work spans 10+ global markets, 137M+ measured users, and has driven decisions from creator selection strategy to budget optimization. Specialties: Causal Inference • Marketing Mix Modeling • Python/SQL • Scalable Data Infrastructure • Full-Funnel Analytics • Audience Modeling
Lead marketing measurement and analytics for Reality Labs' influencer marketing program, delivering causal inference frameworks and strategic insights that drive multi-million-dollar investment decisions. Influencer Marketing Measurement & Strategy • Design and execute causal inference frameworks (PSM, DiD) to measure incremental campaign impact on awareness, consideration, and sales across 10+ global markets (137M+ measured users). • Deliver quarterly incrementality reports that directly inform executive decisions, including multi-million-dollar international budget allocation, creator optimization, and program expansion strategies. • Pioneered audience and creator profiling using ML-based propensity models and follower graph analysis, shaping influencer selection strategy for new product launches. Marketing Mix Modeling & Budget Optimization • Integrated the influencer channel into UberMMM (Meta's Marketing Mix Model), enabling holistic, data-driven allocation across all marketing channels. • Developed a log-based impression decay model for daily cost allocation (R² up to 0.85), improving spend accuracy in cross-channel modeling. Campaign Automation & A/B Testing • Extended the campaign automation platform with automated A/B testing result generation and real-time performance dashboards, further reducing reporting timelines and enabling rapid experimentation. • Dashboard serves 20+ monthly active users as the central source of truth for campaign performance across RL MDS and cross-functional partners.
Embedded within Meta's Reality Labs Marketing Decision Science team as a contract data scientist, focused on building foundational data infrastructure and automated analytics systems from the ground up. Campaign Automation & Dashboard Development • Built an end-to-end campaign automation system that transformed manual reporting workflows — reducing campaign analysis timelines from weeks to days and enabling self-serve analytics for cross-functional partners. • Developed automated dashboards integrating multiple data sources and methodologies, establishing a single source of truth for campaign performance across the organization. Data Infrastructure & Engineering Partnership • Partnered with the Data Engineering team to design and build core data pipelines and infrastructure that powered the team's analytics capabilities. • Created scalable, automated data collection and processing workflows to overcome data fragmentation and enable consistent, reliable measurement. Self-Serve Analytics & Cross-Functional Enablement • Promoted a self-serve analytics model, empowering marketing, partnerships, and strategy teams to access campaign insights independently without DS bottlenecks. • Designed intuitive interfaces and documentation that enabled non-technical stakeholders to leverage data for decision-making.
Advanced Analytics & Business Consultation: Partner with cross-functional business units to define key performance metrics, translating complex business requirements into actionable analytical frameworks, predictive insights, and management-by-exception capabilities. Data Visualization & BI Architecture: Architect, implement, and maintain enterprise-level Business Intelligence (BI) solutions utilizing Tableau. Own the end-to-end administration and optimization of Tableau Server to ensure high-performance data rendering and reliable uptime for executive decision-making. Insight Delivery & Dashboard Engineering: Design and deploy production-grade dashboards, automated alerts, and interactive data products that surface critical business metrics and statistical anomalies to leadership. Data Engineering & Integration: Collabrate across global IT teams to identify, extract, and integrate disparate data assets from multiple legacy and cloud systems, expanding the data warehouse footprint for global reporting and advanced modeling. Statistical Troubleshooting & Root Cause Analysis: Conduct deep-dive root cause analyses on complex data pipelines and system workflows; debug SQL/application code and optimize underlying business processes to ensure data integrity and pipeline reliability. Data Literacy & Stakeholder Enablement: Champion a data-driven culture across the organization by designing and leading technical training programs, empowering business users to leverage advanced analytics tools effectively.
Worked with 4 Black Belts to increase customer experience by reducing the inconsistency in customer complaint process Participated in Gemba event, drew value stream map, SIPOC and CTQC to identify critical quantifiable metrics Built log linear model to analyze survey data and used SAS Exact statement to test the effectiveness of survey responses Used Excel to manipulate case-level datasets, and used Minitab to perform t-tests, ANOVA, Regression and process capability analysis to assess the complaint handling process and identify opportunities to streamline the process
Worked with Strategic Sourcing Manager of International Paper to optimize suppliers’ mix for the purpose of decreasing cost by using regression model to identify critical cost factors Manipulated and imported transaction level dataset (53 variables and 0.5 million observations) to SAS by Proc SQL Built a optimization model using regular regression by SAS Proc Reg, minimizing operating cost by choosing the appropriate suppliers’ mix