Welcome!

Mathematics

I earned a Master of Science in Applied Mathematics degree, specializing in Data Science, from Norhteastern University. I also hold a Bachelor of Arts degree in Pure and Applied Mathematics, with a minor in Computer Science, from Boston University. My academic course selection, work experience, and analytical personality have enabled me to develop a comprehensive understanding of mathematics and computation at scale. My motivation to pursue graduate education comes from a standardized industry need for data-centric individuals who can optimize their work to an unprecedented degree and learn the fundamental methodologies to enable data-driven business success.

Passion

I enjoy exploring the relationships between numbers and translating digits into meaningful stories. These stories become actionable solutions and strategies for businesses, and I take pride in my ability to make data accessible to everyone.These stories become actionable solutions and strategies for businesses and I take pride in my ability to make data accessible to everyone. In a time where understanding and innovating with data has the undeniable potential to improve the way society functions, I aspire to leverage data to drive social change.

Data Science

I have extensive experience leveraging critical data science tools such as Python, R, SQL, and AWS (along with associated packages/libraries) to develop and scale client and internal facing dashboards, carry out extensive exploratory analyses, hack together bots to scrape, clean and process data, and most importantly serve the data needs and requests of c-suite executives, senior management, and data scientists / egnineers to drive product and business success.

May 2022 - Current

• Tech: Python, SQL, MATLAB, AWS (EC2, Redshift, IAM, S3, SageMaker), Apache AirFlow, Apache Spark, DBeaver, GitHub, Tableau (Desktop, Server, Prep), Grafana, JIRA, Excel, YAML

February 2022 - May 2022

• Designed and constructed data pipeline, using MATLAB and Python, to automate hyperparameter tuning for biomedical data models that continuously and non-invasively measure cardio-hemodynamic parameters (i.e., blood pressure) in real-time (cNIBP) via proprietary wrist-wearable technology
• Contributed to all stages of data science initiatives - from clinical data collection, cleaning, and storage (TB scale) to exploratory analysis, visualization, and model implementation
• Collaborated with C-suite executives, senior research scientists, and medical practitioners to build, train, test, and deploy bias resistant data models for clinical user population
• Tech: MATLAB, Python, SQL, GitHub, Jira, Excel, Lucid Chart

July 2021 - December 2021

• Developed an operational performance anomaly detection model to support the solutions that facilitate robot drive issue ticketing and resolution for automated Sortation Centers (SCs)
• Used Jupyter, Python, AWS services(SageMaker, Athena, S3), and machine learning frameworks (scikit-learn) to build, train, validate, and tune multiple data models
• Deployed the data models I developed and tested into production using Java, GIT, Brazil CLI
• Proactively interfaced with various data sources using SQL and Athena, to support SC operation related metric / feature computation, data mining, A/B testing, and modeling
• Collaborated with software / system / data engineers, key stakeholders, and SC operation teams throughout the research and development of data models, metrics, and dashboards
• Tech: Python, Java, SQL, AWS (EC2, Redshift, IAM, S3, SageMaker, DynamoDB, Athena), GitHub, Tableau (Desktop, Server, Prep), Grafana, JIRA, Excel, YAML, Lucid Chart

May 2019 - May 2020

• Developed Spotted’s quarterly celebrity growth momentum metric in order to uphold an exclusive partnership with The Hollywood Reporter and $1.2 million a year in advertising
• Published Analysis: “THR’s Social Climbers.” The Hollywood Reporter 31 July 2019: pp. 75
• Provided clear visualizations and analyses to management and executive-level stakeholders to drive key decisions necessary in the creation of Spotted’s parametric trigger for celebrity disgrace insurance claims
• Created and maintained optimal data pipelines, and implemented scalable automated process to assure efficiency, repeatability, and standardization in the use of data within the Data and Insights team and Spotted as a whole
• Tech: R, SQL, AWS (Redshift), Microsoft SQL Server, GitHub, Crimson Hexagon, Tableau, Excel

June 2018 - May 2019

• Segmented and analyzed millions of data points across hundreds of data features to better assess Hollywood talents’ unique global consumer appeal and recognition, persona, and disgrace risk using R and SQL
• Automated data scraping from Crimson Hexagon platform to facilitate celebrity social media sentiment reporting and reduce data collection errors and extraction time by 6 months
• Implemented dynamic z-score thresholding algorithm to detect anomalous social media negative sentiment spikes using R

March 2018 - May 2018

• Designed and created Python Selenium tests scripts for automating hypothetical user workflows of Catalant’s web-based platform to test feature developments and updates
• Delivered premium, enterprise-ready programs for Solutions clients while testing the newest technology platforms
• Troubleshot and triaged issues with Solutions team to efficiently drive towards feature error identification and resolution

June 2017 - August 2017

• Developed an application for predicting attrition among MMO gamers using the Trendalyze data visualization platform
• Analyzed metadata of 10,000 gamers to pinpoint a set of behavioral characteristics necessary to identify attrition trends
• Performed all necessary data preparation, for uploading gamers’ metadata to Trendalyze platform, using R and SQL

September 2014 - December 2014

• Created and managed a data organization system by backing up data to ensure results always remain accessible for future reference
• Recorded graduate student’s assertions and motives for varying the scope of the research and maintained progress reports
• Analyzed and compiled experimental results and observations using R and Microsoft Excel