Back

Is this algorithm profitable?

I'm working on trading algorithm using AI technique I trade with multiple stocks simultaneously

I get result very close to market index in 4 years . with win rate about 56% and ROI 2% I started with cash 10K .I need evalulation from expert is this alogrithm may be profitable or it just follow market without any real profits

 

Update Backtest








If that's your equity curve I wouldn't advise trading it as is, but that's without knowing any context. Your algo should have a signficant alpha value or otherwise low beta for there to be a point in trading it, and above all a decent Sharpe ratio and low max drawdown. Notice that your equity curve seems to do well a while, then drop off - it's quite typical because many algorithms that used to work years back don't work as of 2017. That said, you might be able to make it smarter.

An easy test is to make random entries and/or exits at the same rate your supposed "smart algo" is making them. If your algo isn't better than randomness, there's no functional difference.

The "proper way" would be to do statistical hypothesis testing but my skills in that area are lacking.

Maybe not related, but worth mentioning: Beware that equity markets have an upward bias over time and a long only algo will have same bias. And, if you're selecting stocks based on membership of some index in 2017 you'll also suffer survivorship bias.

0

Thank you very much  Petter for valuable comments , I worked on enhancing alogorthim but still stuck on sharp drop off periods. and below in algorith result .Appreciate  your feedback  about result and alpha beta values and trading graph below

 

0

There is a recent thread, Any recommended books on algorithm trading strategies?, where Petter has recommended Building Winning Algorithmic Trading Systems by Kevin Davey. We all show read this book, since it shows us how a profitable algorithms looks like.

About your algorthm.
Ask yourself: would you keep your money in something that is losing 2/3 of its value?
This algorithm's drawdown is too big (and there are no fees included yet).

0

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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Update Backtest





0

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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


Loading...

This discussion is closed