• Helping companies understand what resonates most with their audience, by automating A/B tests and combining results into clear feedback about ad features.• Helping improve Generative AI ads by using experiments to refine prompts and seed images.• Tools used: Generative AI, Stable Diffusion, Automated Variable Selection, Explainable Boosting Machine, React, Meta Graph API

• Helped the team understand patterns in revenue, LTV, and marketing spending. Frequently writing internal articles and giving presentations.• Helped centralize revenue, marketing, and supply chain data from across over 10 platforms and 15 countries using Airflow, Dockerized Python scripts, and Stitch Data.• Enabled marketing improvement by forecasting customer lifetime value (CLV / LTV) for each customer daily based on transactional histories.• Techniques and tools used: BTYD / RFM models, BigQuery, Airflow, Stitch Data

• Helped Lift revenue by over $5 million by optimizing regional marketing using experiments, causal inference, and media mix modeling• Wrote over 100 articles and presented to the CEO and Management Team weekly, clearly explaining insights about products, promotions, and marketing• Helped speed up financial reporting, from monthly to daily, by writing a program to combine several cost and revenue datasets• Made accurate company data easily available to the over 100 person organization by building data pipelines and reporting systems• Prioritized projects for the 4 person Data Science team and helped team members grow their skills• Maintained and created projects by writing over 1,000 commits to the company's git repositories• Techniques used: Causal Inference, Media Mix Modeling with Shape and Carryover Effects, Design of Experiments, Product Vectors, Transfer Function-Noise Models,

• Helped improve the site's conversion rate, leading to an increase of more than $20 million in annual revenue, by writing web experiment analysis software using Stan, R, and Bandit Algorithms• Managed our machine learning process by configuring a containerized batch system on AWS which orchestrates over 36 hours of jobs a day• Produced daily sales forecasts and helped explain revenue changes with Bayesian time series analysis• Techniques used: Time Series Analysis, Hierarchical / Multilevel Models, Bayesian State Space Models, Survival Analysis, Probabilistic Programming

• Collaborated across departments and with Professor Alexander Hartemink of Duke University to prototype machine learning features• Built a system which optimizes written content to increase conversion rates• Wrote software to catch errors in large amounts of text• Built a system to make generated text more variable using word embeddings• Techniques used: Contextual Bayesian Bandit Algorithms, Natural Language Processing (NLP), Word Vectors, Probabilistic Programming

• Wrangled and analyzed big datasets regarding patient care, multinational financial flow, TV viewership, and many other topics• Built predictive models and anomaly detectors using time series analysis• Communicated insights with written reports and visualizations• Co-wrote a program that has produced over 6,000 medical clinic reports (Over 80% of clinic managers responded that the reports made understanding the data easier)• Techniques used include: ARIMA Models for Prediction and Anomaly Detection in Times Series, Random Forest Supervised Learning Models, Proportional-Odds Cumulative Logistic Regression, Locally Weighted Regression (loess), Visualizations with D3, R's ggplot, and SVG Vector Graphics

• Studied methods for finding patterns amongst randomness• Focused on data science topics: machine learning, data mining, building predictive models, and supervised and unsupervised statistical learning• Thesis: Built a predictive model with R of the number of views a TED talk will receive• Techniques used include: Generalized Additive Models (GAM) with Smoothing Splines, Cross Validation & Bootstrapping, Hierarchical and K-means Clustering, Multivariate Logistic Regression, ANOVA/MANOVA and Designed Experiments, Poisson Regression, Principle Component Analysis (PCA), Seasonal ARIMA models with Cross Correlations, Intervention Analysis, Ridge & Lasso Regression, Support Vector Machines (SVM)

• Programmed web-apps and websites• Split-tested website designs using quantitative A\B techniques to improve performance