Publicado em June 15, 2020

Artificial Intelligence and the performance of QUANTS Funds

Investment funds in the financial market that use algorithms for decision making are already a reality

My interest in algorithms and mathematical models started at the Faculty of Engineering in the mid-1980s. My undergraduate thesis used modeling to calibrate the oven temperature controllers used by the Department of Chemistry. At that time, computing power was very limited. The algorithms were written in C and assembly language and ran on a Zilog Z80 CPU.

I started studying quantum funds last year, but my curiosity grew after taking the Coursera course “Using Machine Learning in Trading and Finance”. I decided to research more about the algorithms employed, available APIs and to study existing funds abroad and in Brazil. One of the pioneers in this area is the Medalion Fund by Renaissance Technologies LLC, by mathematician Jim Simons whose story I will tell below.

 James Harris (Jim) Simons is a mathematician graduated from MIT, born in 1938. In 1982, after a career that included the American Security Agency (NSA), Jim created the “Renaissance Technologies LLC”, a specialized Hedge Fund for use quantitative models derived from analyzes using mathematics and statistics. In 1988, the firm created the “Medallion Fund”, which used algorithms perfected by the team of scientists hired by Renaissance.

Medallion Funds is considered to be one of the most successful funds in the world. Investing in treasuries, commodities, derivatives and foreign exchange, the fund yielded 2480% to its shareholders in the period from 1989 to 1999 and even in the 2008 stock market crisis, it showed significant profit. The fund is closed to outside investors and has earned more than $ 100B in profit since its creation. It is part of a Renaissance portfolio that includes 3 other funds that total more than $ 55B of equity.

 Renaissance employs more than 200 specialists who are not trained in finance, including mathematicians, physicists and statisticians, and at least a third of them have PhDs. The firm uses “Quantitative trading” working on huge volumes of data using scalable processing architectures and hundreds proprietary algorithms.

 Jim Simons, has a fortune estimated by Forbes at around 22BU $ and is currently engaged in philanthropy through the Simons Foundation including the “Math for America” initiative to recruit and retain high quality math teachers for New York schools. York. Anyone who is curious to know more about him, can watch the TED “A rare interview with the mathematician who broke Wall Street”.

 Advances in Artificial Intelligence, machine learning and the availability of cloud computing resources have contributed to increasing the potential of these algorithms and significantly reducing implementation costs by accelerating their adoption by the financial community.

There are currently several APIs of quantitative algorithms for those who want to create a model. Some are free, available in the Open Source model, others paid as those from the company QuantHouse. To find them, just search on Google and you will have access to extensive documentation on their features and tutorials on how to use them. There are also companies specializing in education in this area. In addition to the course mentioned at the beginning of the story, QuantStart is worth checking out.

In Brazil we have some companies specialized in Quantum Funds including Pandhora, Giant Steps Capital, Murano Investimentos, Kadima Asset Management and SmartQuant investments. Find out more about them in the links below and evaluate the performance of the funds in different market situations.

I also include here some books that may interest those who want to go deeper into the topic:

“The man who solved the Market: How Jim Simons Launched the Quant Revolution”,

“The Quants: How a new Breed of Math Whizzes Conquered Wall Street and Nearly Destroyed it”,

“Flashboys. Cracking the Money code (available in Portuguese and English) and

“Fortune’s Formula. The untold story of the scientific betting that beat the casinos and Wall Street ”

Have fun.

157 reads 69 Likes

About the author

Marco Lauria

Marco Lauria

A.I. Advisor @ I2AI

Read too

157 reads 69 Likes
4th Artificial Intelligence Symposium
Próximo Evento
June 21, 2021

4th Artificial Intelligence Symposium

The IV Intelligence Symposium held by I2AI in partnership with ECA-USP promotes two days of lectures and debates on the latest trends in AI. The first day is entirely dedicated