Scraping the SEC
Open-sourced cleaned and parsed financial statements filed between 2013-2016
Posts by Collection
portfolio
projects
Transfer learning
Training a student VGG-16 neural network with a teacher AlexNet
Random Rocket stuff
High-level summaries of my work done at an online travel agency
protein
Markov State Models for Molecular Dynamics
Using probabilistic graph models for efficient simulation of the protein folding process
Komen for the Cure: A new campaign against cancer
This was a paper I wrote as a freshman undergraduate which ended up becoming the leading article in Stern’s annual “Call for Corporate Action” publication (mirror here). My research for the paper is where I first got interested in the quantitative sciences - before that, I was fully intent on pursuing a path of “business” and “entrepreneurship” (whatever that meant to my addled freshman mind). It’s a quaint and nostalgic experience to read my past opinions, so I like keeping this around as a reminder of where I came from.
publications
ranking
Ranking at Rocket
Slide deck of the first ranking model deployed at Rocketmiles
Measuring the Business Value of a Hotel Ranking Model
In this blog post, I talk about the ranking model in layman’s terms. How does it learn? How can we interpret the model’s definition of a “good” model?
Learning to Rank Hotels
Benchmark of deep learning methods for recommender systems on the Rocket hotel ranking dataset
Why we chose LambdaMART for our hotel ranking model
In this blog post, I talk about LambdaMART, a listwise ranking model based on gradient boosting which has been used in AirBnB and Microsoft. What is its objective function optimizing for? How can we update it to handle display bias? And in what situation would you use it over a collaborative filtering approach?