Back

Market following algo

Hi all,

I have created an algo which simply follows the market. Reverse or Directional. For example, you simply chose an equity and algo will trade it. The returns chart will be similar to the price chart of the equity and highly correlated. It's like SPY vs SPX correlation which means, works like an ETF.

In the other hand, if equity lose during this time, algo will lose too. This is a buy only algo and works with stocks, futures, forex and every other tradable assets. If you like to go reverse of the equitie's chart, algo will short instead of long.

Ok here's the point of this post. Are such algos common or unusual? And useful?

Here are some screenshots

 

---
Total pos: 503 / 25.49%
Won: 321 / 63.82%
Lost: 181
Max won: 13.860000000000014
Max lost: 17.610000000000014
Longs / wins: 503 321
Shorts / wins: 0 0
Avg. Profit: 1.69028
Avg. Loss: 1.78308
---
Hold Min/Max/Avg/Total: 1 29 2 1404
RRR: 0.95
Profit Factor: 1.68
Profit: 219.8426
Profit Mean: 0.4379334661354569
Profit STD: 2.5392883804560413

--- BENCHMARK (BUY & HOLD) ---
BUY & HOLD : 172.13 USD
ALGO Returns : 219.84 USD
Diff : 47.71 USD

 

Thanks,

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.


Hi Atilla,

i don't quite understand the strategy of your algo, maybe you can explain it in clearer way ? Statistics seem decent though.

0

Hi Kenneth,

Thank you for your comment. I have combined ML and AI to create an algo. What i did here is simply traded the signals created by algo (backtest). Eventually, my earnings (tick) end up as shown in the chart (second plot - Returns). The plot of earnings looks like the chart itself. If you compare Returns and Chart itself, you can easily see it. I'm wondering if this is a common issue? I'm not very confident and will not trade this. Not yet! Because, if market sell of, algo will lose. It simply follows the market not the trend. If I chose to short instead of long, the chart of returns will be reversed and there will be negative correlation.

I hope I'm clear.

0

Is this built in QuantConnect Atilla Yurtseven ?

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.


Hi Jared,

Not yet. I'm planning to write this code in QC but the training part should be hard to do. I'm not familiar with the framework.

0

Somehow, the screenshots i have shared not available anymore

0

Anything that generates alpha is useful. Using machine learning and artificial intelligence puts you ahead of the curve. A lot of algorithms go long only. Some algorithms attempt to generate profits while creating market neutral positions (longing their highest ranked candidates and shorting their lowest ranked candidates) but this is not necessary. 

0

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