Back to all posts

Algorithm Development Competition with Upgrade Capital

It's a problem — students interested in exploring career opportunities in quantitative finance often do not know where to start. It's difficult to gain access to recent non-academic quantitative research, and doing hands-on work requires significant investment of time, money — or both.

At Quantopian, we encourage people to expand their understanding of quantitative finance by providing free, accessible educational resources, as well as a community of peers and experts. Take a look at our community and you’ll see plenty of examples of collaboration and people tackling challenges together. This commitment to education is the motivation behind a partnership with Upgrade Capital to enable all students with an interest in quantitative finance to gain hands-on experience in the field through an algorithm development competition. The competition will also help the industry identify exceptional young quants on the basis of their work rather than their resumes.

Our platform is an excellent starting point for exploring the practical applications of quantitative finance, because it allows anyone with a working knowledge of Python to dive right into the source code for existing trading algorithms and begin tweaking. Upgrade Capital caters to students with pre-existing code libraries or making use of data inaccessible through the Quantopian platform. During the out-of-sample testing period (May 6th through June 7th), these students will be asked to submit their orders to Upgrade through a proprietary virtual portfolio management API.

So here are the details on the competition:

Restrictions

Students are allowed to trade all US exchange-listed stocks, ADRs, and ETFs. Shorting is allowed but leverage is not.

Trade volumes for orders submitted through the Upgrade Capital API are limited on the basis of available liquidity; you can read more about Upgrade's platform here.

Timeframe

I. Development

Students will have until 11:59pm PST on May 5th to develop and backtest a trading algorithm. This work can either be done on Quantopian's platform or offline.

Each competition participant is required to submit a document explaining their algorithm and its performance in backtests no later than 11:59pm PST on May 12th.

II. Testing

Algorithm performance from May 6th until market close on June 7th will be used as an out-of-sample test. Competition participants may submit a supplementary note explaining performance during this period but all documentation needs to be received no later than 11:59pm PST on June 16th.

III. Evaluation

As no single metric provides a comprehensive understanding of performance, winners will be selected by a panel of traders and risk management experts on the basis of their write-ups as well multi-dimensional analyses of each competition participant's performance.

The names of competition winners will be announced on June 21st. The winners will then be publicly profiled through both Upgrade Capital and Quantopian.

How to Sign Up

Registration for the Spring 2013 Algorithmic Trading Competition ends at 11:59pm PST on April 14th. If you would like to participate, please sign up here.



The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian.

In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.

Tybalt Trust

So...you develop, test and then submit a thesis to "The Man" who then gives you a price should you win? Do you have to reveal the algorithim to anyone? How do you protect IP?

For this competition, you do have to reveal the algorithm. The judges evaluate the algos based on returns and the algo's concepts.

As a general policy on Quantopian, your IP is yours, private and protected. The obvious exception to that is if you share your algorithm with the Quantopian community. At that point you still own the IP, but it is no longer private.

In the case of this competition, submitting an entry includes agreeing to share the algo with the judges.

so its a funny case of I want to win but I do not want to perform to the best of my abilities because if I do so, they see my strategies and then I lose in the long term. But then the assumption is that if I can make that good a strategy, why would I be entering this competition. So this competition pitches me against trading wannabees who do not know they are that good. the other category of strategy developers are those that have too many strategies at their disposal and they have some good ones which they are not trading right now so just use it in the competition. but then trading wannabees do not stand a chance against them at all. hence if a trading wannabe competes, he will never be able to win this competition. so the best way to judge a competition like this is not to declare a first, second and a third but to call anybody whose strategy beats the index by more than alpha a winner or to select a percentile of participants and call them winners, whichever is higher. But it will be better if these announcements are made beforehand.

@sidquanto - I would not be so quick to dismiss those new to the field. One of the first kids I met when I began reaching out to universities two years ago had built a fully functioning NLP based trading algorithm at 18. Side-note: he happens to have no qualms about making public the work he does on Quantopian.

In terms of the methodology you propose for evaluating competition participants - anyone can data-snoop their way to amazing alpha. Even if you are adding a lengthy out-of-sample testing period, given enough people tossing coins, a few of them will come out looking like they are really good at getting tails.

What matters most is sophistication in the underlying algorithm. What we are looking for is not so much high (risk adjusted) alpha but evidence of deep insight into financial markets and an ability to translate it into actionable strategies. To put it differently, we are not asking anyone to give us the algo they have spent the past few years polishing - but merely to show how they would go about constructing and refining an algorithm more or less from scratch. We are not looking to steal anyone's IP but merely to recognise a few truly exceptional young people.

Comments are closed.