Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Next step

Hi,

Anybody have any idea what I could explore next on my algorithm to make it better? If it were not for the 2008 crash it would not make as much money.

1 response

Hi Luis,

Great question. Here's what I would do, all of these steps are also detailed here https://www.quantopian.com/posts/using-alternative-data-researching-and-implementing-a-market-neutral-strategy. Please see that post for reference.

Also, keep in mind that a useful way to think about quant strategy development is following framework. You are trying to maximize your novel alpha, while keeping risk exposures below set thresholds. Every investor's risk tolerances will be different, but the principle holds. Alpha is defined as returns that are left over when you remove dependency on known risk factors (https://www.quantopian.com/lectures/factor-risk-exposure). Known risk factors include things like: market returns, market cap returns, momentum returns, mean reversion returns, etc. In general you don't want your returns to be dependent on those things as they are well known and not useful to an investor. A great strategy will be independent of changes in known risk factors, the market being one of the most common offenses. Other risk constraints include things like position concentration (https://www.quantopian.com/lectures/position-concentration-risk), sector neutrality, etc.

  1. Run a Pyfolio tearsheet of your backtest to analyze exposures. Determine if your exposures are within risk tolerances.
  2. Develop more factors in an effort to improve and diversify your predictions. Factors can be evaluated using alphalens (https://www.quantopian.com/lectures/factor-analysis).
  3. Combine the factors into your template.
  4. Repeat the process of coming up with new hypotheses/factors and ensuring that they don't have high exposures to known risk factors until the algorithm's overall risk exposures are below tolerances.
Disclaimer

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.