Software Developer in New York, NY, United States

I built an algorithmic news feed for the financial market news. The public version is offline, but a demo is available on request.

This project involved visualization of the financial Twittersphere in early 2019; specifically, people who tweet about financial news (clustered by topics, force-directed graphs, word clouds, similar users, and key metrics).

An overview of the classification methods and application to a factor investing problem.

Historically, what would have been the optimal allocation and spending plan for retirement?

If you are maximally risk-averse, the Bengen 4% rule holds up: start by spending 4% of your portfolio and increase annually for inflation. If you are less risk-averse, a more flexible rule like a fixed spending amount plus a percentage of assets might make more sense.

Using TensorFlow, we explore the universe of stock/bond allocations and spending rules to find the plan that would have maximized certainty-equivalent spending, at various levels of risk aversion.

I wrote a blog post exploring analogies between investing and playing the game of poker. Both are games of quantitative thinking about imperfect information and psychology. But real-world markets don't reward bluffers.

This is a thought experiment on what would happen if more and more people invest passively. There's no such thing as a 100% purely passive investor: we are free to pick a strategy but not avoiding the choice. As more people invest more passively, they save on expenses, but market efficiency decreases. The ideal "Warren Buffett" active investor can always exploit any "suckers." At some point, though, the less active investing there is, the more excellent opportunities there are for remaining active investors to exploit.

Here on a blog entry, I had fun with topic modeling, clustering, Word2vec, and text generation with fund names.

An overview of deep reinforcement learning, code examples with OpenAI gym Cartpole and LunarLander, and code to implement policy gradient on market data, with positive results on simulated data (Ornstein–Uhlenbeck mean reversion process and noise).

A platform that allows users to search on Google Maps, Yelp, and Foursquare for a keyword like 'Pizza'. The construct combined Bayesian ranking, display table, and results on a map.
Back end stack: Python, Flask, deployed as a Docker microservice in Amazon ECS.
Front end stack: Bootstrap, jQuery, Leaflet.js.