I am a problem solver at heart and am always on the lookout for interesting problems and even more interesting/elegant solutions. As an engineer by schooling, I made the transition to the data field after falling in love with data-driven modeling, reasoning, and decision making.

I am a data scientist at Morgan Stanley focusing on NLP and helping research new tools and practices to generate $\alpha$. I got my master's from The Cooper Union (see coursework), where I worked on a augmenting satellite imagery streams through cross-sensor, past, and future assisted deep-learning-based image synthesis (synthesizing high resolution satellite images at un-imaged times by levaraging past/future imagery and a 2nd satellite looking at the same location).

I get excited about learning new things, cooking/food, and the potential of data.

Find me on Linkedin.

Learning to learn outside of the schooling system and focusing on becoming a more well-rounded, thoughtful person.

School was great for me, but it also only exposed me to very niche information and ideas. After graduating and pushing to continue down a similar route to my education, I felt myself growing complacent. It felt too comfortable. I was going deeper and deeper into known territory and confirming my understandings. I was going nowhere. I am now pushing to do differently - to challenge my comfort zone with what I learn, to re-consider my ideas and beliefs, and to work on being more thoughtful and openminded.

• 📜 30DaysOfCode October 2021+ (Data skills, Machine Learning, Visualization, Coding Fundementals) - Documented daily progress and worked through personal projects.

• 🛰️ S.P.P.P.A.C.Y. (Deep Learning, Feature Engineering, Data Collection, Data Wrangling, Visualization) - Full stack data science project to take satellite imagery and predict crop-yield on a per-pixel basis without being biased by current land usage [Final Presentation] [Report].

• 📈 Data Science for Social Good (Data Exploration, Data Modeling, Data Analysis, Machine Learning, Visualization) - Volunteer work to interpret data and increase costumer retention. The analysis we performed helped the team redesign their intake surveys and got the upper management to hire full-time data scientists!

• 💃 DanceMuse (Automation, Data Pipelines, Audio Manipulation, Pose Extraction, Dance Generation, Deep Learning) - Increased the ease of use of dance-generation deep learning models so they can be a tool for the artist community [Repo] [Final Presentation].

• 🛡️ DefensiveLayer (Deep Learning, Adversarial Attacks, Defence Against Adversarial Attacks) - Investigated intra-network layers as a way to defend against adversarial attacks, turns out they help! (but also reduce accuracy, so this ends up being a tradeoff) [Final Presentation] [Report].

• 💰 Financial Signal Processing (course) (Time-Series Analysis, Monte Carlo Simulations, Stochastic Differential Equations) - Finance and financial data-based projects using signal processing.