Alphien and Global Precious Metals launched the Precious Metals Allocation Competition on Nov. 25th. The competition is open to all the data scientists around the world, where the participants have the chance to build a dynamic, long-only, fully-invested allocation between gold, silver, platinum and palladium with a limited drawdown.
As for the prize, the winner will get a 100g Gold Bar and the 2nd best participant will get a Canadian Maple leaf ½ ounce Gold Coin. Also, the participants could get their strategies licensed by the sponsor and earn the licensing fees.
The leaderboards are live, and the ranking is based on quantitative metrics only. With the new Alphien points distribution system, the top 5 participants with the best performing strategies will have the opportunity to earn points every week to exchange them for special features that will allow the participants to improve their strategies and climb up in the leaderboard.
To check the details of the competition, click on the link here.
More about Alphien and the latest competition
Alphien is redefining finance by its open innovation concept where all data scientists from different industries can participate in contributing to the adoption of data science in asset management. For that, Alphien, based in Paris and Singapore, offers an interactive platform where the most talented researchers around the world build algorithms and innovative solutions to tackle financial real life challenges through competitions, and also to help the asset management companies improve their quantitative investment processes.
Currently, more than 3,700 data scientists are registered in the platform, including students and professional researchers, and with the help of the Alphien Quant team, their strategies are reviewed, tested and paper replicated so they can share their ideas with the quant community or earn licensing fees.
The competition had 2 rounds. In the first round, the data scientists participated in two competitions:
- Outperform the SP 500 index: to build a systematic stock picking portfolio, while using machine learning to make the most favorable selection;
- Machine Learning for Complex Pricing Models: to build machine learning models that are able to predict the price of an equity structured product faster than traditional models.
In the last round, the finalist participated in a 3 live hackathon: Enhanced FX strategy, where the participants had the chance to work with UBS mentors to build a diversified currency trading strategy, taking advantage of interest rates spreads between currencies, while controlling the volatility of the FX portfolio.