QUANTCONNECT COMMUNITY
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.
Eugene Kuzmin
@henry-h_2 Unbelievable performance!
Out of curiosity, how do you manage such a large decision tree?Â
- Decisions: **54**
- Ranking filters: **9**
- Allocation groups: **100**
- Asset leaves: **146**
- Unique tickers: **44**
Â
Oleg Roshka
Thanks for publishing this, Henry. I kept the decision-tree and sleeve structure while remediating history ordering/readiness, horizon consistency, selected-asset scoring, risk-adjusted ranking, and volatility/concentration controls. No slippage or market-impact model was added.
For transparency, the full recent 2021-01-01 to 2026-05-15 remediated run returned 26.612%, with Sharpe 0.020, 29.7% drawdown, 2,775 orders and $2,825.94 fees. QuantConnect requires Sharpe >= 0.4 and more than 1,275 days for library publication, so the published 2016-2021 window was selected post hoc specifically to meet both gates; it returned 88.830%, with Sharpe 0.653 and 21.6% drawdown. Many assets in the current universe had not launched during that older window. The caveats and both samples are disclosed here: https://www.quantconnect.com/strategies/702/Gold-Miner---Remediated-Variant . Independent out-of-sample validation remains appropriate.
Eugene Kuzmin
Henry H Â I translated the strategy into Python, meaning there is no TREE_JSON. Would you like to see the code?
Henry H
Yes of course!
Matevz Nolimal
Can you please share it here?
Eugene Kuzmin
Eugene Kuzmin
Doesn't publish the strategy URL. Â Anyway, it's public.
QuantConnect Reconciliation
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.
To unlock posting to the community forums please complete at least 30% of Boot Camp.
You can continue your Boot Camp training progress from the terminal. We hope to see you in the community soon!