About Me

Skills

Programming

Python

SQL

Docker

Bash

R

Technologies

Anaconda

Azure DevOps

Databricks

Git

Linux

PowerBI

VS Code

Statistics & ML

Anomaly Detection

Classification

Clustering

Deep Neural Networks (TensorFlow-Keras)

Locality Sensitive Hashing

Naïve Bayes

Natural Language Processing (NLTK, spaCy)

PySpark

Scikit-Learn

Experience

Machine Learning Engineer II - Data Scientist

Circana (Formerly NPD Group)

New York, NY
11/2021 — present
  • Research and develop unsupervised anomaly detection methods to score hierarchical time-series anomalies
  • Develop univariate and multivariate scoring metrics, ranking algorithms for model selection and model results
  • Refactor disparate teams’ existing anomaly detection codebases into a single unified framework
  • Engineer SQL queries and stored procedures, automate ETL processes for data science analyses and reporting
  • Design and implement a scalable DAG pipeline using object-oriented best practices and SOLID design principles
  • Reduce model runtime by 94% by implementing multiprocessing, dynamic imports, and lazy execution
  • Reduce noise in text features by 12% by engineering a battery of semi-supervised and unsupervised methods
  • Research and deploy Word Segmentation, Word Sense Disambiguation, and OCR error correction techniques
  • Automate training and logging of mlflow experiments of custom meta-classifiers on Azure Databricks
  • Develop custom transformers and estimators in Python, leveraging inheritance from Scikit-Learn base classes
  • Spearhead documentation effort by developing internal standards for code development and documentation
  • Author and maintain Data Science team’s Wiki pages for project descriptions and research logging

Process Control & Operations Analyst

NPD Group

Port Washington, NY
08/2019 — 11/2021
  • Implemented automated solutions to address key pain points in collaboration with multiple process leads
  • Automated data validation using Python and Selenium, resulting in new client contracts
  • Developed a Python script to to reduce monthly manual hours spent on open-end survey responses translation by 75%

Summer Associate

NPD Group

Port Washington, NY
06/2019 — 08/2019
  • Enhanced data consistency by normalizing large corpora of brand names and retailer names using Python
  • Scripted monthly data quality and schema integrity checks for staging server of flat file reports
  • Presented project results and actionable next steps to senior leadership and executives

Education

M.S. Data Science

St. John's University

Queens, NY

B.S., Computer Science

St. John's University

Queens, NY

Interests

In my free time, I enjoy exploring the outdoors, traveling, and reading. My passion for technology extends beyond my professional life, as I’m always eager to discover new tech and find innovative ways to apply my skills. I also love playing the ukulele and sharing fun moments with my adorable cat, Asparagus.

Contact

If you'd like to get in touch, discuss my work, or explore collaboration opportunities, you can find my contact information and social media profiles below.