Mark Best

The code I developed is associated with a study that predicts the likelihood of successfully funding a Kickstarter project. The study specifically analyzes the project descriptions and aims to identify whether keywords significantly impact funding outcomes. Interestingly, the analysis revealed that specific keywords like "Arduino" or "craft beer" are considerably more popular among funded projects compared to their respective base categories.

The code extracts keywords from project descriptions and determines which keywords appear disproportionately more frequently in either the "funded" or "not funded" category. The probability of such disproportional occurrence, evaluated using a Bernoulli distribution, serves as the information ratio for each keyword. A higher information ratio indicates the keyword's greater usefulness in predicting funding success.

Rust is an interesting language and one that I think will improve the algorithmic trading space. Most high-frequency trading platforms are low latency asynchronous messaging systems. Rust's type safety and fearless concurrency make building high-performance, highly concurrent, multi-threaded messaging systems without much pain in alternative languages such as C++. Also, given the lack of run time and garbage collector, the system's latency is not only low but doesn't suffer from latency spikes caused by the GC. This was a great project for Rust and one that has really made me fall in love with it.

The project was a greenfield implementation of an algorithmic trading platform for trading cryptocurrencies across different exchanges. This work included exchange connectivity, strategy development, operational tooling for monitoring and control, and accounting software for investors.