Mar 2020 – Mar 2022 · 2 yrs · Culver City, California, United States

• Served as tech lead for recommendations, user propensity, and LTV models across Apple Music, TV+, and App Store.

Jan 2019 – Jan 2020 · 1 yr · Greater New York City Area

• Productionized Churn, Lead Scoring and Sales Forecasting models
• AI Data Science Conference in Jerusalem (2019): Presented novel Bayesian encoding method for categorical variables: https://arxiv.org/abs/1904.13001

Jan 2018 – Jan 2019 · 1 yr · Greater New York City Area

• Working on a cross functional team on a wide range of projects including:
• An internal Growth Model to model the effects of marketing spend and optimally allocate goals
• Optimal SKU planning for offices in new locations
• Time to Event modeling for conversion
• Modeling lead paths with Recurrent Neural Networks
• NLP and Topic Modeling of Resumes and Job descriptions

Feb 2017 – May 2018 · 1 yr 3 mos · Greater New York City Area

• Developed various data products for clients ranging in industry from Pharmaceuticals to CPG
• Helped with Airflow ETL implementations for several fortune 100 clients
• Contributed algorithms and provided support for an internal advanced analytics library

Sep 2016 – Aug 2018 · 1 yr 11 mos · Greater Boston Area

• - Developing software to model clinical supply chains with Agent Based Simulation and Monte Carlo methods. Try it out here! http://simplexcs.com/

Jun 2016 – Aug 2016 · 2 mos · Greater New York City Area

• Built and implemented various machine learning models for Rite Aid Pharmacy including Gaussian Naïve Bayes, Logistic Regression, and Random Forest in order to predict whether a customer will enroll in certain initiatives.
• Presented analysis and the data product to executive management with recommendations for implementation.
• Provided advanced ad hoc analytics including a matching algorithm to find a control group for a federal grant study

Jan 2016 – Jun 2016 · 5 mos · Greater Boston Area

• Developed Python software for time series forecasting of clinical Oncology trials’ medication supplies.
• Customized algorithms including Dynamic Time Warping Nearest Neighbor for classification, Holt-Winters and non-linear regression for forecasting, and the Bootstrap and Delta method for confidence intervals

May 2014 – Dec 2015 · 1 yr 7 mos · Greater New Orleans Area

• Developed a mobile application for IOS and Android that recommends craft beers based on a user's taste preferences and location.
• Launched and managed a successful Kickstarter campaign.
• Hired and managed a team of database administrators, authors, and graphic designers.