Copper Challenge

Introduction

Description

Investment universe

Data

Benchmark

No benchmark (your implicit benchmark is a cash position in US dollars).

Portfolio constraints

Each time the weights are set, the following constraints must be satisfied (i.e. the constraints are not checked between 2 set dates):

Ticker	Min	Max
LP	-100%	100%

Additional notes:

• Weights have to be between -1 and 1
• First weights have to be generated before/on 2004-01-02 (1 year calibration/training. Rolling/expanding windows are allowed)
• Sharpe Ratio for the backtest period has to be > 0.25
• Payout has to be replicable and contain no lookahead bias
• All time series data has to be called via the DataFeatures object - no data calls in your payout.
• Payout and its dependencies have to be attached and properly documented
• Short summary of your model to be written at the start of the notebook -- Summary can include model used, why the model was selected, rationale for any data processing done, parameter selection etc...
• Whole notebook has to be ran under 15 mins (excluding the testCopperSubmission function). Training of models/processing of data inclusive.
• Only notebook that are well documented, code with clear comments will be accepted. The notebook need to explain the rationale of your approach and why you are using the techniques. A lack of clear documentation can induce disqualification even if your version of notebook has been accepted, make your code easily readable and clear to understand, create functions or classes to make your notebook cleaner. Also, put potential references in your notebooks.

Please also have a look at the payout pitfalls page for common issues faced by users.

Strategy transactions

Transaction costs: 1 basis point (bp) of the amount being transacted.

Transaction frequency: The maximum transaction frequency is daily (no intraday trades). All trades are executed at market close prices.

Transaction signals: Transaction signals must be based on data available at close-of-business on the day prior to the execution. Signals are 'executed' 1 day after they are generated. Please have a look at this page for more information on our '1-day lag convention'.

Rebalancing penalty: 2 basis points on the total AUM, each time you have a date with a set of weights, it will be considered as a 'rebalancing' day and you will incur the penalty. Please check the example notebook and check the page Rebalancing and transactions costs

Backtest period

The in-sample period runs from 1 Jan 2003 to 31 Dec 2018. To prevent any overfitting of the models, data for 2016-2018 will only be unveiled after your first model submission.

Note: Once your first submission is approved, you can revise it as much as you want.

Submissions

You must use Notebook to submit your solution. You can only submit one notebook. However, there is no limitation in the number of revisions you can make on a submitted notebook. If the solution follows a theoretical or academic paper, the participants are encouraged to attach the document with the submission, any relevant document (own paper or other document) to explain the approach used will increase the robustness scoring.

Please visit our Submissions page for all details on how to submit.

---

The winner(s) will receive either:

an iPad Air 64GB WIFI (team of one person), or

an Apple Watch model SE GPS 40 mm per team member (teams of 2 or 3 members).

• The opportunity to get your strategy licensed by Asset Managers looking for such asset allocation strategies

---